�ݺ�ߣshows by User: BillLiu31

�ݺ�ߣshows by User: BillLiu31 / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: BillLiu31 / Tue, 23 Aug 2022 21:44:58 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: BillLiu31 Walk Through a Real World ML Production Project /slideshow/walk-through-a-real-world-ml-production-project/252669132 w2022082310wallaroo-220823214458-86cae5cc
Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform. Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn: The current pain points and blockers to production The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate How the DS uploads and deploys models to WL performing simple validation checks on output How the ML Engineer can check model health (inference speed, etc) How the DS checks logs, looks for anomalies How the DS switches model in the pipeline Speakers: Nina Zumel, Martin Bald ]]>
Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform. Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn: The current pain points and blockers to production The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate How the DS uploads and deploys models to WL performing simple validation checks on output How the ML Engineer can check model health (inference speed, etc) How the DS checks logs, looks for anomalies How the DS switches model in the pipeline Speakers: Nina Zumel, Martin Bald ]]> Tue, 23 Aug 2022 21:44:58 GMT /slideshow/walk-through-a-real-world-ml-production-project/252669132 BillLiu31@slideshare.net(BillLiu31) Walk Through a Real World ML Production Project BillLiu31 Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform. Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn: The current pain points and blockers to production The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate How the DS uploads and deploys models to WL performing simple validation checks on output How the ML Engineer can check model health (inference speed, etc) How the DS checks logs, looks for anomalies How the DS switches model in the pipeline Speakers: Nina Zumel, Martin Bald <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/w2022082310wallaroo-220823214458-86cae5cc-thumbnail.jpg?width=120&height=120&fit=bounds" /> Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform. Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn: The current pain points and blockers to production The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate How the DS uploads and deploys models to WL performing simple validation checks on output How the ML Engineer can check model health (inference speed, etc) How the DS checks logs, looks for anomalies How the DS switches model in the pipeline Speakers: Nina Zumel, Martin Bald

Walk Through a Real World ML Production Project from Bill Liu

]]> 22 0 https://cdn.slidesharecdn.com/ss_thumbnails/w2022082310wallaroo-220823214458-86cae5cc-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Redefining MLOps with Model Deployment, Management and Observability in Production /slideshow/redefining-mlops-with-model-deployment-management-and-observability-in-production/251862772 aicamppresentationwallaroo5242022-220526171312-a5ca4017
Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410 What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change? The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly. In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss: - How to track the ongoing accuracy of their models in production - How to immediately detect drift before it causes significant damage to the business - How to locate the cause of model drifting in live environments. We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case. Speaker: Younes Amar, Head of Product Wallaroo AI. Resources: https://docs.wallaroo.ai/]]>
Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410 What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change? The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly. In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss: - How to track the ongoing accuracy of their models in production - How to immediately detect drift before it causes significant damage to the business - How to locate the cause of model drifting in live environments. We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case. Speaker: Younes Amar, Head of Product Wallaroo AI. Resources: https://docs.wallaroo.ai/]]> Thu, 26 May 2022 17:13:12 GMT /slideshow/redefining-mlops-with-model-deployment-management-and-observability-in-production/251862772 BillLiu31@slideshare.net(BillLiu31) Redefining MLOps with Model Deployment, Management and Observability in Production BillLiu31 Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410 What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change? The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly. In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss: - How to track the ongoing accuracy of their models in production - How to immediately detect drift before it causes significant damage to the business - How to locate the cause of model drifting in live environments. We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case. Speaker: Younes Amar, Head of Product Wallaroo AI. Resources: https://docs.wallaroo.ai/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aicamppresentationwallaroo5242022-220526171312-a5ca4017-thumbnail.jpg?width=120&height=120&fit=bounds" /> Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410 What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change? The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly. In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss: - How to track the ongoing accuracy of their models in production - How to immediately detect drift before it causes significant damage to the business - How to locate the cause of model drifting in live environments. We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case. Speaker: Younes Amar, Head of Product Wallaroo AI. Resources: https://docs.wallaroo.ai/

Redefining MLOps with Model Deployment, Management and Observability in Production from Bill Liu

]]> 113 0 https://cdn.slidesharecdn.com/ss_thumbnails/aicamppresentationwallaroo5242022-220526171312-a5ca4017-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Productizing Machine Learning at the Edge /slideshow/productizing-machine-learning-at-the-edge/250519291 veraserdiukovaproductizinglearningattheedge-211025060814
These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development. In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles. https://www.aicamp.ai/event/eventdetails/W2021102210]]>
These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development. In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles. https://www.aicamp.ai/event/eventdetails/W2021102210]]> Mon, 25 Oct 2021 06:08:14 GMT /slideshow/productizing-machine-learning-at-the-edge/250519291 BillLiu31@slideshare.net(BillLiu31) Productizing Machine Learning at the Edge BillLiu31 These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development. In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles. https://www.aicamp.ai/event/eventdetails/W2021102210 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/veraserdiukovaproductizinglearningattheedge-211025060814-thumbnail.jpg?width=120&height=120&fit=bounds" /> These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development. In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles. https://www.aicamp.ai/event/eventdetails/W2021102210

Productizing Machine Learning at the Edge from Bill Liu

]]> 250 0 https://cdn.slidesharecdn.com/ss_thumbnails/veraserdiukovaproductizinglearningattheedge-211025060814-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Transformers in Vision: From Zero to Hero /slideshow/transformers-in-vision-from-zero-to-hero/250429627 transformersinvisionaicamp-211012172343
Attention Is All You Need. With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks? These and many other questions will be answered during the talk. In this tech talk, we will discuss: - A piece of history: Why did we need a new architecture? - What is self-attention, and where does this concept come from? - The Transformer architecture and its mechanisms - Vision Transformers: An Image is worth 16x16 words - Video Understanding using Transformers: the space + time approach - The scale and data problem: Is Attention what we really need? - The future of Computer Vision through Transformers Speaker: Davide Coccomini, Nicola Messina Website: https://www.aicamp.ai/event/eventdetails/W2021101110 ]]>
Attention Is All You Need. With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks? These and many other questions will be answered during the talk. In this tech talk, we will discuss: - A piece of history: Why did we need a new architecture? - What is self-attention, and where does this concept come from? - The Transformer architecture and its mechanisms - Vision Transformers: An Image is worth 16x16 words - Video Understanding using Transformers: the space + time approach - The scale and data problem: Is Attention what we really need? - The future of Computer Vision through Transformers Speaker: Davide Coccomini, Nicola Messina Website: https://www.aicamp.ai/event/eventdetails/W2021101110 ]]> Tue, 12 Oct 2021 17:23:42 GMT /slideshow/transformers-in-vision-from-zero-to-hero/250429627 BillLiu31@slideshare.net(BillLiu31) Transformers in Vision: From Zero to Hero BillLiu31 Attention Is All You Need. With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks? These and many other questions will be answered during the talk. In this tech talk, we will discuss: - A piece of history: Why did we need a new architecture? - What is self-attention, and where does this concept come from? - The Transformer architecture and its mechanisms - Vision Transformers: An Image is worth 16x16 words - Video Understanding using Transformers: the space + time approach - The scale and data problem: Is Attention what we really need? - The future of Computer Vision through Transformers Speaker: Davide Coccomini, Nicola Messina Website: https://www.aicamp.ai/event/eventdetails/W2021101110 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/transformersinvisionaicamp-211012172343-thumbnail.jpg?width=120&height=120&fit=bounds" /> Attention Is All You Need. With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks? These and many other questions will be answered during the talk. In this tech talk, we will discuss: - A piece of history: Why did we need a new architecture? - What is self-attention, and where does this concept come from? - The Transformer architecture and its mechanisms - Vision Transformers: An Image is worth 16x16 words - Video Understanding using Transformers: the space + time approach - The scale and data problem: Is Attention what we really need? - The future of Computer Vision through Transformers Speaker: Davide Coccomini, Nicola Messina Website: https://www.aicamp.ai/event/eventdetails/W2021101110

Transformers in Vision: From Zero to Hero from Bill Liu

]]> 3104 0 https://cdn.slidesharecdn.com/ss_thumbnails/transformersinvisionaicamp-211012172343-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Deep AutoViML For Tensorflow Models and MLOps Workflows /slideshow/deep-autoviml-for-tensorflow-models-and-mlops-workflows/249949216 deepautovimlpresentationfullaug2021-210810030815
deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself! In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains. https://www.aicamp.ai/event/eventdetails/W2021080918]]>
deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself! In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains. https://www.aicamp.ai/event/eventdetails/W2021080918]]> Tue, 10 Aug 2021 03:08:15 GMT /slideshow/deep-autoviml-for-tensorflow-models-and-mlops-workflows/249949216 BillLiu31@slideshare.net(BillLiu31) Deep AutoViML For Tensorflow Models and MLOps Workflows BillLiu31 deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself! In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains. https://www.aicamp.ai/event/eventdetails/W2021080918 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/deepautovimlpresentationfullaug2021-210810030815-thumbnail.jpg?width=120&height=120&fit=bounds" /> deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself! In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains. https://www.aicamp.ai/event/eventdetails/W2021080918

Deep AutoViML For Tensorflow Models and MLOps Workflows from Bill Liu

]]> 314 0 https://cdn.slidesharecdn.com/ss_thumbnails/deepautovimlpresentationfullaug2021-210810030815-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Metaflow: The ML Infrastructure at Netflix /slideshow/metaflow-the-ml-infrastructure-at-netflix/249929198 aicampaugust2021metaflow-210806043512
Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning. Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate. In this talk, you will learn about: - What to expect from a modern ML infrastructure stack. - Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix. - Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies. https://www.aicamp.ai/event/eventdetails/W2021080510]]>
Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning. Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate. In this talk, you will learn about: - What to expect from a modern ML infrastructure stack. - Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix. - Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies. https://www.aicamp.ai/event/eventdetails/W2021080510]]> Fri, 06 Aug 2021 04:35:11 GMT /slideshow/metaflow-the-ml-infrastructure-at-netflix/249929198 BillLiu31@slideshare.net(BillLiu31) Metaflow: The ML Infrastructure at Netflix BillLiu31 Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning. Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate. In this talk, you will learn about: - What to expect from a modern ML infrastructure stack. - Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix. - Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies. https://www.aicamp.ai/event/eventdetails/W2021080510 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aicampaugust2021metaflow-210806043512-thumbnail.jpg?width=120&height=120&fit=bounds" /> Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning. Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate. In this talk, you will learn about: - What to expect from a modern ML infrastructure stack. - Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix. - Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies. https://www.aicamp.ai/event/eventdetails/W2021080510

Metaflow: The ML Infrastructure at Netflix from Bill Liu

]]> 644 0 https://cdn.slidesharecdn.com/ss_thumbnails/aicampaugust2021metaflow-210806043512-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Practical Crowdsourcing for ML at Scale /slideshow/practical-crowdsourcing-for-ml-at-scale/249824880 aicamptoloka-210721172730
AI stands on three pillars: algorithms, hardware and training data. While the first two have already become commodities on the market, the latter - reliable labelled data - is still a bottleneck in the industry. Need to add twice as much data to the training set to improve your model? Want to validate the accuracy of a new classificator in an hour? Or maybe you are building a human-in-the-loop process with 90% of cases processed automatically and the trickiest 10% of cases fine-tuned by people in real time. You can do it all with crowdsourcing, but only with crowdsourcing done right. In this talk, we will discuss how the new generation of methods and tools allows to collect high quality human labelled data on a large scale and why every ML specialist should know how to use crowdsourcing. You will learn from the talk: * Understand the applicability, benefits and limits of the crowdsourcing approach. * Integrate an on-demand workforce into your processes and build human-in-the-loop processes. * Control the quality and accuracy of data labeling to develop high performing ML models. * Understand the full-cycle crowdsourcing project Speaker: Daria Baidakova(Toloka)]]>
AI stands on three pillars: algorithms, hardware and training data. While the first two have already become commodities on the market, the latter - reliable labelled data - is still a bottleneck in the industry. Need to add twice as much data to the training set to improve your model? Want to validate the accuracy of a new classificator in an hour? Or maybe you are building a human-in-the-loop process with 90% of cases processed automatically and the trickiest 10% of cases fine-tuned by people in real time. You can do it all with crowdsourcing, but only with crowdsourcing done right. In this talk, we will discuss how the new generation of methods and tools allows to collect high quality human labelled data on a large scale and why every ML specialist should know how to use crowdsourcing. You will learn from the talk: * Understand the applicability, benefits and limits of the crowdsourcing approach. * Integrate an on-demand workforce into your processes and build human-in-the-loop processes. * Control the quality and accuracy of data labeling to develop high performing ML models. * Understand the full-cycle crowdsourcing project Speaker: Daria Baidakova(Toloka)]]> Wed, 21 Jul 2021 17:27:29 GMT /slideshow/practical-crowdsourcing-for-ml-at-scale/249824880 BillLiu31@slideshare.net(BillLiu31) Practical Crowdsourcing for ML at Scale BillLiu31 AI stands on three pillars: algorithms, hardware and training data. While the first two have already become commodities on the market, the latter - reliable labelled data - is still a bottleneck in the industry. Need to add twice as much data to the training set to improve your model? Want to validate the accuracy of a new classificator in an hour? Or maybe you are building a human-in-the-loop process with 90% of cases processed automatically and the trickiest 10% of cases fine-tuned by people in real time. You can do it all with crowdsourcing, but only with crowdsourcing done right. In this talk, we will discuss how the new generation of methods and tools allows to collect high quality human labelled data on a large scale and why every ML specialist should know how to use crowdsourcing. You will learn from the talk: * Understand the applicability, benefits and limits of the crowdsourcing approach. * Integrate an on-demand workforce into your processes and build human-in-the-loop processes. * Control the quality and accuracy of data labeling to develop high performing ML models. * Understand the full-cycle crowdsourcing project Speaker: Daria Baidakova(Toloka) <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aicamptoloka-210721172730-thumbnail.jpg?width=120&height=120&fit=bounds" /> AI stands on three pillars: algorithms, hardware and training data. While the first two have already become commodities on the market, the latter - reliable labelled data - is still a bottleneck in the industry. Need to add twice as much data to the training set to improve your model? Want to validate the accuracy of a new classificator in an hour? Or maybe you are building a human-in-the-loop process with 90% of cases processed automatically and the trickiest 10% of cases fine-tuned by people in real time. You can do it all with crowdsourcing, but only with crowdsourcing done right. In this talk, we will discuss how the new generation of methods and tools allows to collect high quality human labelled data on a large scale and why every ML specialist should know how to use crowdsourcing. You will learn from the talk: * Understand the applicability, benefits and limits of the crowdsourcing approach. * Integrate an on-demand workforce into your processes and build human-in-the-loop processes. * Control the quality and accuracy of data labeling to develop high performing ML models. * Understand the full-cycle crowdsourcing project Speaker: Daria Baidakova(Toloka)

Practical Crowdsourcing for ML at Scale from Bill Liu

]]> 230 0 https://cdn.slidesharecdn.com/ss_thumbnails/aicamptoloka-210721172730-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Building large scale transactional data lake using apache hudi /slideshow/building-large-scale-transactional-data-lake-using-apache-hudi/247459593 buildinglargescaletransactionaldatalakeusingapachehudi-210430181618
Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes. In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel. We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases. Speaker: Satish Kotha (Uber) Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore. website: https://www.aicamp.ai/event/eventdetails/W2021043010]]>
Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes. In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel. We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases. Speaker: Satish Kotha (Uber) Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore. website: https://www.aicamp.ai/event/eventdetails/W2021043010]]> Fri, 30 Apr 2021 18:16:18 GMT /slideshow/building-large-scale-transactional-data-lake-using-apache-hudi/247459593 BillLiu31@slideshare.net(BillLiu31) Building large scale transactional data lake using apache hudi BillLiu31 Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes. In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel. We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases. Speaker: Satish Kotha (Uber) Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore. website: https://www.aicamp.ai/event/eventdetails/W2021043010 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/buildinglargescaletransactionaldatalakeusingapachehudi-210430181618-thumbnail.jpg?width=120&height=120&fit=bounds" /> Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes. In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel. We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases. Speaker: Satish Kotha (Uber) Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore. website: https://www.aicamp.ai/event/eventdetails/W2021043010

Building large scale transactional data lake using apache hudi from Bill Liu

]]> 854 0 https://cdn.slidesharecdn.com/ss_thumbnails/buildinglargescaletransactionaldatalakeusingapachehudi-210430181618-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Deep Reinforcement Learning and Its Applications /slideshow/deep-reinforcement-learning-and-its-applications/247362291 rl-applications20210428-210429180344
What is the most exciting AI news in recent years? AlphaGo! What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)! What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics. In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios. https://www.aicamp.ai/event/eventdetails/W2021042818]]>
What is the most exciting AI news in recent years? AlphaGo! What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)! What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics. In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios. https://www.aicamp.ai/event/eventdetails/W2021042818]]> Thu, 29 Apr 2021 18:03:44 GMT /slideshow/deep-reinforcement-learning-and-its-applications/247362291 BillLiu31@slideshare.net(BillLiu31) Deep Reinforcement Learning and Its Applications BillLiu31 What is the most exciting AI news in recent years? AlphaGo! What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)! What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics. In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios. https://www.aicamp.ai/event/eventdetails/W2021042818 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/rl-applications20210428-210429180344-thumbnail.jpg?width=120&height=120&fit=bounds" /> What is the most exciting AI news in recent years? AlphaGo! What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)! What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics. In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios. https://www.aicamp.ai/event/eventdetails/W2021042818

Deep Reinforcement Learning and Its Applications from Bill Liu

]]> 1221 0 https://cdn.slidesharecdn.com/ss_thumbnails/rl-applications20210428-210429180344-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Big Data and AI in Fighting Against COVID-19 /slideshow/big-data-and-ai-in-fighting-against-covid19/236820502 dataandaiforcovid-19-200711225452
Website: https://learn.xnextcon.com/event/eventdetails/W20070810 As the COVID-19 pandemic sweeps the globe, big data and AI have emerged as crucial tools for everything from diagnosis and epidemiology to therapeutic and vaccine development. In this talk, we collect and review how big data is fighting back against COVID-19. We also provide a deep diving for two interesting use cases: 1) Use NLP and BERT to answer scientific questions. 2) Covid-19 data lake from Databricks, Google and Amazon Agenda: Introduction Supercomputers for Scientific Research Covid-19 Tracking and Prediction Covid-19 Research and Diagnosis Use Case 1 NLP and BERT to answer scientific questions Use Case 2 Covid-19 Data Lake and Platform]]>
Website: https://learn.xnextcon.com/event/eventdetails/W20070810 As the COVID-19 pandemic sweeps the globe, big data and AI have emerged as crucial tools for everything from diagnosis and epidemiology to therapeutic and vaccine development. In this talk, we collect and review how big data is fighting back against COVID-19. We also provide a deep diving for two interesting use cases: 1) Use NLP and BERT to answer scientific questions. 2) Covid-19 data lake from Databricks, Google and Amazon Agenda: Introduction Supercomputers for Scientific Research Covid-19 Tracking and Prediction Covid-19 Research and Diagnosis Use Case 1 NLP and BERT to answer scientific questions Use Case 2 Covid-19 Data Lake and Platform]]> Sat, 11 Jul 2020 22:54:52 GMT /slideshow/big-data-and-ai-in-fighting-against-covid19/236820502 BillLiu31@slideshare.net(BillLiu31) Big Data and AI in Fighting Against COVID-19 BillLiu31 Website: https://learn.xnextcon.com/event/eventdetails/W20070810 As the COVID-19 pandemic sweeps the globe, big data and AI have emerged as crucial tools for everything from diagnosis and epidemiology to therapeutic and vaccine development. In this talk, we collect and review how big data is fighting back against COVID-19. We also provide a deep diving for two interesting use cases: 1) Use NLP and BERT to answer scientific questions. 2) Covid-19 data lake from Databricks, Google and Amazon Agenda: Introduction Supercomputers for Scientific Research Covid-19 Tracking and Prediction Covid-19 Research and Diagnosis Use Case 1 NLP and BERT to answer scientific questions Use Case 2 Covid-19 Data Lake and Platform <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/dataandaiforcovid-19-200711225452-thumbnail.jpg?width=120&height=120&fit=bounds" /> Website: https://learn.xnextcon.com/event/eventdetails/W20070810 As the COVID-19 pandemic sweeps the globe, big data and AI have emerged as crucial tools for everything from diagnosis and epidemiology to therapeutic and vaccine development. In this talk, we collect and review how big data is fighting back against COVID-19. We also provide a deep diving for two interesting use cases: 1) Use NLP and BERT to answer scientific questions. 2) Covid-19 data lake from Databricks, Google and Amazon Agenda: Introduction Supercomputers for Scientific Research Covid-19 Tracking and Prediction Covid-19 Research and Diagnosis Use Case 1 NLP and BERT to answer scientific questions Use Case 2 Covid-19 Data Lake and Platform

Big Data and AI in Fighting Against COVID-19 from Bill Liu

]]> 652 2 https://cdn.slidesharecdn.com/ss_thumbnails/dataandaiforcovid-19-200711225452-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Highly-scalable Reinforcement Learning RLlib for Real-world Applications /slideshow/highlyscalable-reinforcement-learning-rllib-for-realworld-applications/233597534 rllib-reinforcementlearningwithray-aicamp-2020-05-11-200511203622
website: https://learn.xnextcon.com/event/eventdetails/W20051110 video: https://www.youtube.com/watch?v=8tG8PJC6oaU In reinforcement learning (RL), an agent learns how to optimize performance solely by collecting experience in the real world or via a simulator. RL is being applied to problems such as decision making, process optimization (e.g., manufacturing and supply chains), ad serving, recommendations, self-driving cars, and algorithmic trading. In this talk, I will discuss RLlib, a reinforcement learning library built on Ray with a strong focus on large-scale execution and scalability, ease-of-use for general users, as well as customizability for developers and researchers. RLlib offers autonomous task-learning via many common RL algorithms and it scales from a laptop to a cluster with hundreds of machines. It is used by dozens of organizations, from startups to research labs to large organizations. You will see RLlib in action with a live demo.]]>
website: https://learn.xnextcon.com/event/eventdetails/W20051110 video: https://www.youtube.com/watch?v=8tG8PJC6oaU In reinforcement learning (RL), an agent learns how to optimize performance solely by collecting experience in the real world or via a simulator. RL is being applied to problems such as decision making, process optimization (e.g., manufacturing and supply chains), ad serving, recommendations, self-driving cars, and algorithmic trading. In this talk, I will discuss RLlib, a reinforcement learning library built on Ray with a strong focus on large-scale execution and scalability, ease-of-use for general users, as well as customizability for developers and researchers. RLlib offers autonomous task-learning via many common RL algorithms and it scales from a laptop to a cluster with hundreds of machines. It is used by dozens of organizations, from startups to research labs to large organizations. You will see RLlib in action with a live demo.]]> Mon, 11 May 2020 20:36:22 GMT /slideshow/highlyscalable-reinforcement-learning-rllib-for-realworld-applications/233597534 BillLiu31@slideshare.net(BillLiu31) Highly-scalable Reinforcement Learning RLlib for Real-world Applications BillLiu31 website: https://learn.xnextcon.com/event/eventdetails/W20051110 video: https://www.youtube.com/watch?v=8tG8PJC6oaU In reinforcement learning (RL), an agent learns how to optimize performance solely by collecting experience in the real world or via a simulator. RL is being applied to problems such as decision making, process optimization (e.g., manufacturing and supply chains), ad serving, recommendations, self-driving cars, and algorithmic trading. In this talk, I will discuss RLlib, a reinforcement learning library built on Ray with a strong focus on large-scale execution and scalability, ease-of-use for general users, as well as customizability for developers and researchers. RLlib offers autonomous task-learning via many common RL algorithms and it scales from a laptop to a cluster with hundreds of machines. It is used by dozens of organizations, from startups to research labs to large organizations. You will see RLlib in action with a live demo. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/rllib-reinforcementlearningwithray-aicamp-2020-05-11-200511203622-thumbnail.jpg?width=120&height=120&fit=bounds" /> website: https://learn.xnextcon.com/event/eventdetails/W20051110 video: https://www.youtube.com/watch?v=8tG8PJC6oaU In reinforcement learning (RL), an agent learns how to optimize performance solely by collecting experience in the real world or via a simulator. RL is being applied to problems such as decision making, process optimization (e.g., manufacturing and supply chains), ad serving, recommendations, self-driving cars, and algorithmic trading. In this talk, I will discuss RLlib, a reinforcement learning library built on Ray with a strong focus on large-scale execution and scalability, ease-of-use for general users, as well as customizability for developers and researchers. RLlib offers autonomous task-learning via many common RL algorithms and it scales from a laptop to a cluster with hundreds of machines. It is used by dozens of organizations, from startups to research labs to large organizations. You will see RLlib in action with a live demo.

Highly-scalable Reinforcement Learning RLlib for Real-world Applications from Bill Liu

]]> 282 0 https://cdn.slidesharecdn.com/ss_thumbnails/rllib-reinforcementlearningwithray-aicamp-2020-05-11-200511203622-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Build computer vision models to perform object detection and classification with AWS /slideshow/build-computer-vision-models-to-perform-object-detection-and-classification-with-aws/232886685 ramine-tinati-aicamp-computervision-200430035929-200430055907
event: https://learn.xnextcon.com/event/eventdetails/W20042918 video: description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios. In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification. Key Takeaways: Understand the history of Computer Vision Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models How to orchestrate multiple models for implementing a real-world use case]]>
event: https://learn.xnextcon.com/event/eventdetails/W20042918 video: description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios. In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification. Key Takeaways: Understand the history of Computer Vision Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models How to orchestrate multiple models for implementing a real-world use case]]> Thu, 30 Apr 2020 05:59:07 GMT /slideshow/build-computer-vision-models-to-perform-object-detection-and-classification-with-aws/232886685 BillLiu31@slideshare.net(BillLiu31) Build computer vision models to perform object detection and classification with AWS BillLiu31 event: https://learn.xnextcon.com/event/eventdetails/W20042918 video: description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios. In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification. Key Takeaways: Understand the history of Computer Vision Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models How to orchestrate multiple models for implementing a real-world use case <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ramine-tinati-aicamp-computervision-200430035929-200430055907-thumbnail.jpg?width=120&height=120&fit=bounds" /> event: https://learn.xnextcon.com/event/eventdetails/W20042918 video: description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios. In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification. Key Takeaways: Understand the history of Computer Vision Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models How to orchestrate multiple models for implementing a real-world use case

Build computer vision models to perform object detection and classification with AWS from Bill Liu

]]> 260 0 https://cdn.slidesharecdn.com/ss_thumbnails/ramine-tinati-aicamp-computervision-200430035929-200430055907-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Causal Inference in Data Science and Machine Learning /slideshow/causal-inference-in-data-science-and-machine-learning/232322567 causalinferenceinmachinelearning-200420182949
Event: https://learn.xnextcon.com/event/eventdetails/W20042010 Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability. In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex. ]]>
Event: https://learn.xnextcon.com/event/eventdetails/W20042010 Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability. In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex. ]]> Mon, 20 Apr 2020 18:29:49 GMT /slideshow/causal-inference-in-data-science-and-machine-learning/232322567 BillLiu31@slideshare.net(BillLiu31) Causal Inference in Data Science and Machine Learning BillLiu31 Event: https://learn.xnextcon.com/event/eventdetails/W20042010 Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability. In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/causalinferenceinmachinelearning-200420182949-thumbnail.jpg?width=120&height=120&fit=bounds" /> Event: https://learn.xnextcon.com/event/eventdetails/W20042010 Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability. In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex.

Causal Inference in Data Science and Machine Learning from Bill Liu

]]> 363 0 https://cdn.slidesharecdn.com/ss_thumbnails/causalinferenceinmachinelearning-200420182949-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Weekly #106: Deep Learning on Mobile /slideshow/weekly-106-deep-learning-on-mobile/231514881 w20040610deeplearningonmobile-200406205838
https://learn.xnextcon.com/event/eventdetails/W20040610 This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone; The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world. ]]>
https://learn.xnextcon.com/event/eventdetails/W20040610 This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone; The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world. ]]> Mon, 06 Apr 2020 20:58:38 GMT /slideshow/weekly-106-deep-learning-on-mobile/231514881 BillLiu31@slideshare.net(BillLiu31) Weekly #106: Deep Learning on Mobile BillLiu31 https://learn.xnextcon.com/event/eventdetails/W20040610 This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone; The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/w20040610deeplearningonmobile-200406205838-thumbnail.jpg?width=120&height=120&fit=bounds" /> https://learn.xnextcon.com/event/eventdetails/W20040610 This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone; The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world.

Weekly #106: Deep Learning on Mobile from Bill Liu

]]> 191 1 https://cdn.slidesharecdn.com/ss_thumbnails/w20040610deeplearningonmobile-200406205838-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning /slideshow/autoviz-and-autoviml-visualization-and-machine-learning/231470133 autovizandautovimlautovisualizationandmlmarch2020-200406035817
https://learn.xnextcon.com/event/eventdetails/W20040310 I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.]]>
https://learn.xnextcon.com/event/eventdetails/W20040310 I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.]]> Mon, 06 Apr 2020 03:58:16 GMT /slideshow/autoviz-and-autoviml-visualization-and-machine-learning/231470133 BillLiu31@slideshare.net(BillLiu31) Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning BillLiu31 https://learn.xnextcon.com/event/eventdetails/W20040310 I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/autovizandautovimlautovisualizationandmlmarch2020-200406035817-thumbnail.jpg?width=120&height=120&fit=bounds" /> https://learn.xnextcon.com/event/eventdetails/W20040310 I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.

Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning from Bill Liu

]]> 178 0 https://cdn.slidesharecdn.com/ss_thumbnails/autovizandautovimlautovisualizationandmlmarch2020-200406035817-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 AISF19 - On Blending Machine Learning with Microeconomics /slideshow/aisf19-on-blending-machine-learning-with-microeconomics/188872730 jordan-ucb-191031072912
Michael Jordan, UC Berkeley http://aisf19.xnextcon.com ]]>
Michael Jordan, UC Berkeley http://aisf19.xnextcon.com ]]> Thu, 31 Oct 2019 07:29:12 GMT /slideshow/aisf19-on-blending-machine-learning-with-microeconomics/188872730 BillLiu31@slideshare.net(BillLiu31) AISF19 - On Blending Machine Learning with Microeconomics BillLiu31 Michael Jordan, UC Berkeley http://aisf19.xnextcon.com <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/jordan-ucb-191031072912-thumbnail.jpg?width=120&height=120&fit=bounds" /> Michael Jordan, UC Berkeley http://aisf19.xnextcon.com

AISF19 - On Blending Machine Learning with Microeconomics from Bill Liu

]]> 346 4 https://cdn.slidesharecdn.com/ss_thumbnails/jordan-ucb-191031072912-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 AISF19 - Travel in the AI-First World /slideshow/aisf19-travel-in-the-aifirst-world/188871951 luyuanfangainextcon-2019-191031072626
http://aisf19.xnextcon.com Luyuan Fang, Head of AI labs/VP, Expedia Group]]>
http://aisf19.xnextcon.com Luyuan Fang, Head of AI labs/VP, Expedia Group]]> Thu, 31 Oct 2019 07:26:25 GMT /slideshow/aisf19-travel-in-the-aifirst-world/188871951 BillLiu31@slideshare.net(BillLiu31) AISF19 - Travel in the AI-First World BillLiu31 http://aisf19.xnextcon.com Luyuan Fang, Head of AI labs/VP, Expedia Group <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/luyuanfangainextcon-2019-191031072626-thumbnail.jpg?width=120&height=120&fit=bounds" /> http://aisf19.xnextcon.com Luyuan Fang, Head of AI labs/VP, Expedia Group

AISF19 - Travel in the AI-First World from Bill Liu

]]> 261 2 https://cdn.slidesharecdn.com/ss_thumbnails/luyuanfangainextcon-2019-191031072626-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 AISF19 - Unleash Computer Vision at the Edge /slideshow/aisf19-unleash-computer-vision-at-the-edge/188871085 stevegriset-alwaysai-191031072312
Steve Griset, alwaysAI http://aisf19.xnextcon.com]]>
Steve Griset, alwaysAI http://aisf19.xnextcon.com]]> Thu, 31 Oct 2019 07:23:12 GMT /slideshow/aisf19-unleash-computer-vision-at-the-edge/188871085 BillLiu31@slideshare.net(BillLiu31) AISF19 - Unleash Computer Vision at the Edge BillLiu31 Steve Griset, alwaysAI http://aisf19.xnextcon.com <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/stevegriset-alwaysai-191031072312-thumbnail.jpg?width=120&height=120&fit=bounds" /> Steve Griset, alwaysAI http://aisf19.xnextcon.com

AISF19 - Unleash Computer Vision at the Edge from Bill Liu

]]> 221 0 https://cdn.slidesharecdn.com/ss_thumbnails/stevegriset-alwaysai-191031072312-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeFlow, Airflow, and MLflow /slideshow/aisf19-building-scalable-kubernetesnative-mlai-pipelines-with-tfx-kubeflow-airflow-and-mlflow/188871077 chrisfreglypipelineai-191031072310
by Chris Fregly, PipelineAI http://aisf19.xnextcon.com]]>
by Chris Fregly, PipelineAI http://aisf19.xnextcon.com]]> Thu, 31 Oct 2019 07:23:10 GMT /slideshow/aisf19-building-scalable-kubernetesnative-mlai-pipelines-with-tfx-kubeflow-airflow-and-mlflow/188871077 BillLiu31@slideshare.net(BillLiu31) AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeFlow, Airflow, and MLflow BillLiu31 by Chris Fregly, PipelineAI http://aisf19.xnextcon.com <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/chrisfreglypipelineai-191031072310-thumbnail.jpg?width=120&height=120&fit=bounds" /> by Chris Fregly, PipelineAI http://aisf19.xnextcon.com

AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeFlow, Airflow, and MLflow from Bill Liu

]]> 414 4 https://cdn.slidesharecdn.com/ss_thumbnails/chrisfreglypipelineai-191031072310-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Toronto meetup 20190917 /slideshow/toronto-meetup-20190917/176520493 torontomeetup20190917-190927002459
https://www.meetup.com/aittg-toronto/events/264394399/]]>
https://www.meetup.com/aittg-toronto/events/264394399/]]> Fri, 27 Sep 2019 00:24:59 GMT /slideshow/toronto-meetup-20190917/176520493 BillLiu31@slideshare.net(BillLiu31) Toronto meetup 20190917 BillLiu31 https://www.meetup.com/aittg-toronto/events/264394399/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/torontomeetup20190917-190927002459-thumbnail.jpg?width=120&height=120&fit=bounds" /> https://www.meetup.com/aittg-toronto/events/264394399/

Toronto meetup 20190917 from Bill Liu

]]> 404 3 https://cdn.slidesharecdn.com/ss_thumbnails/torontomeetup20190917-190927002459-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://public.slidesharecdn.com/v2/images/profile-picture.png https://cdn.slidesharecdn.com/ss_thumbnails/w2022082310wallaroo-220823214458-86cae5cc-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/walk-through-a-real-world-ml-production-project/252669132 Walk Through a Real Wo... https://cdn.slidesharecdn.com/ss_thumbnails/aicamppresentationwallaroo5242022-220526171312-a5ca4017-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/redefining-mlops-with-model-deployment-management-and-observability-in-production/251862772 Redefining MLOps with ... https://cdn.slidesharecdn.com/ss_thumbnails/veraserdiukovaproductizinglearningattheedge-211025060814-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/productizing-machine-learning-at-the-edge/250519291 Productizing Machine L...