�ݺ�ߣshows by User: nervanasys

�ݺ�ߣshows by User: nervanasys / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: nervanasys / Tue, 30 May 2017 20:19:13 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: nervanasys Introduction to Deep Learning and neon at Galvanize /slideshow/introduction-to-deep-learning-and-neon-at-galvanize/76499620 galvanizedl-170530201913
Kyle Ambert leads a deep learning with neon workshop at Galvanize in San Francisco]]>
Kyle Ambert leads a deep learning with neon workshop at Galvanize in San Francisco]]> Tue, 30 May 2017 20:19:13 GMT /slideshow/introduction-to-deep-learning-and-neon-at-galvanize/76499620 nervanasys@slideshare.net(nervanasys) Introduction to Deep Learning and neon at Galvanize nervanasys Kyle Ambert leads a deep learning with neon workshop at Galvanize in San Francisco <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/galvanizedl-170530201913-thumbnail.jpg?width=120&height=120&fit=bounds" /> Kyle Ambert leads a deep learning with neon workshop at Galvanize in San Francisco

Introduction to Deep Learning and neon at Galvanize from Intel Nervana

]]> 1449 8 https://cdn.slidesharecdn.com/ss_thumbnails/galvanizedl-170530201913-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 Women in AI kickoff /slideshow/women-in-ai-kickoff/76499535 womeninaikickoffslidesall-170530201553
The first Women in AI meetup kicked off in Santa Clara with Julie Choi and Anahita Bhiwandiwalla telling their AI stories.]]>
The first Women in AI meetup kicked off in Santa Clara with Julie Choi and Anahita Bhiwandiwalla telling their AI stories.]]> Tue, 30 May 2017 20:15:53 GMT /slideshow/women-in-ai-kickoff/76499535 nervanasys@slideshare.net(nervanasys) Women in AI kickoff nervanasys The first Women in AI meetup kicked off in Santa Clara with Julie Choi and Anahita Bhiwandiwalla telling their AI stories. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/womeninaikickoffslidesall-170530201553-thumbnail.jpg?width=120&height=120&fit=bounds" /> The first Women in AI meetup kicked off in Santa Clara with Julie Choi and Anahita Bhiwandiwalla telling their AI stories.

Women in AI kickoff from Intel Nervana

]]> 418 5 https://cdn.slidesharecdn.com/ss_thumbnails/womeninaikickoffslidesall-170530201553-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 Intel Nervana Artificial Intelligence Meetup 1/31/17 /slideshow/intel-nervana-artificial-intelligence-meetup-13117/71651355 20170121startupmlconf-170201192357
Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. In this talk, we will give an overview of Nervana’s DL platform and get some hands-on experience using this platform to train and execute deep learning models. Speaker: Will Constable Join our Meetup Group: https://www.meetup.com/SV-Deep-Learning/]]>
Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. In this talk, we will give an overview of Nervana’s DL platform and get some hands-on experience using this platform to train and execute deep learning models. Speaker: Will Constable Join our Meetup Group: https://www.meetup.com/SV-Deep-Learning/]]> Wed, 01 Feb 2017 19:23:57 GMT /slideshow/intel-nervana-artificial-intelligence-meetup-13117/71651355 nervanasys@slideshare.net(nervanasys) Intel Nervana Artificial Intelligence Meetup 1/31/17 nervanasys Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. In this talk, we will give an overview of Nervana’s DL platform and get some hands-on experience using this platform to train and execute deep learning models. Speaker: Will Constable Join our Meetup Group: https://www.meetup.com/SV-Deep-Learning/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/20170121startupmlconf-170201192357-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. In this talk, we will give an overview of Nervana’s DL platform and get some hands-on experience using this platform to train and execute deep learning models. Speaker: Will Constable Join our Meetup Group: https://www.meetup.com/SV-Deep-Learning/

Intel Nervana Artificial Intelligence Meetup 1/31/17 from Intel Nervana

]]> 2644 4 https://cdn.slidesharecdn.com/ss_thumbnails/20170121startupmlconf-170201192357-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 Introduction to deep learning @ Startup.ML by Andres Rodriguez /nervanasys/introduction-to-deep-learning-startupml-by-andres-rodriguez 20170121startupmlconf-170123231139
Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel offers various software and hardware to support a diversity of workloads and user needs. Intel Nervana delivers a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. This platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.]]>
Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel offers various software and hardware to support a diversity of workloads and user needs. Intel Nervana delivers a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. This platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.]]> Mon, 23 Jan 2017 23:11:39 GMT /nervanasys/introduction-to-deep-learning-startupml-by-andres-rodriguez nervanasys@slideshare.net(nervanasys) Introduction to deep learning @ Startup.ML by Andres Rodriguez nervanasys Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel offers various software and hardware to support a diversity of workloads and user needs. Intel Nervana delivers a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. This platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/20170121startupmlconf-170123231139-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel offers various software and hardware to support a diversity of workloads and user needs. Intel Nervana delivers a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. This platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.

Introduction to deep learning @ Startup.ML by Andres Rodriguez from Intel Nervana

]]> 2317 5 https://cdn.slidesharecdn.com/ss_thumbnails/20170121startupmlconf-170123231139-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 Andres Rodriguez at AI Frontiers: Catalyzing Deep Learning's Impact in the Enterprise /slideshow/andres-rodriguez-at-ai-frontiers-catalyzing-deep-learnings-impact-in-the-enterprise/71192202 20170111aifrontiers-170119165251
Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.]]>
Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.]]> Thu, 19 Jan 2017 16:52:51 GMT /slideshow/andres-rodriguez-at-ai-frontiers-catalyzing-deep-learnings-impact-in-the-enterprise/71192202 nervanasys@slideshare.net(nervanasys) Andres Rodriguez at AI Frontiers: Catalyzing Deep Learning's Impact in the Enterprise nervanasys Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/20170111aifrontiers-170119165251-thumbnail.jpg?width=120&height=120&fit=bounds" /> Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data.

Andres Rodriguez at AI Frontiers: Catalyzing Deep Learning's Impact in the Enterprise from Intel Nervana

]]> 2332 2 https://cdn.slidesharecdn.com/ss_thumbnails/20170111aifrontiers-170119165251-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 Intel Nervana Artificial Intelligence Meetup 11/30/16 /slideshow/intel-nervana-artificial-intelligence-meetup-113016/69926555 meetup11301-161207190211
End-to-end speech recognition in Neon presented by Anthony Ndirango and Tyler Lee Modern automatic speech recognition systems incorporate tremendous amount of expert knowledge and a wide array of machine learning techniques. The promise of deep learning is to strip away much of this complexity in favor of the flexibility of neural networks. We will describe our efforts in implementing end-to-end speech recognition in neon by combining convolutional and recurrent neural networks to create an acoustic model followed by a graph-based decoding scheme. These types of models are trained to go directly from raw waveforms to transcribed speech without requiring any kind of explicit forced alignment. We will also discuss additional challenges that must be overcome to produce state-of-the-art results. ]]>
End-to-end speech recognition in Neon presented by Anthony Ndirango and Tyler Lee Modern automatic speech recognition systems incorporate tremendous amount of expert knowledge and a wide array of machine learning techniques. The promise of deep learning is to strip away much of this complexity in favor of the flexibility of neural networks. We will describe our efforts in implementing end-to-end speech recognition in neon by combining convolutional and recurrent neural networks to create an acoustic model followed by a graph-based decoding scheme. These types of models are trained to go directly from raw waveforms to transcribed speech without requiring any kind of explicit forced alignment. We will also discuss additional challenges that must be overcome to produce state-of-the-art results. ]]> Wed, 07 Dec 2016 19:02:11 GMT /slideshow/intel-nervana-artificial-intelligence-meetup-113016/69926555 nervanasys@slideshare.net(nervanasys) Intel Nervana Artificial Intelligence Meetup 11/30/16 nervanasys End-to-end speech recognition in Neon presented by Anthony Ndirango and Tyler Lee Modern automatic speech recognition systems incorporate tremendous amount of expert knowledge and a wide array of machine learning techniques. The promise of deep learning is to strip away much of this complexity in favor of the flexibility of neural networks. We will describe our efforts in implementing end-to-end speech recognition in neon by combining convolutional and recurrent neural networks to create an acoustic model followed by a graph-based decoding scheme. These types of models are trained to go directly from raw waveforms to transcribed speech without requiring any kind of explicit forced alignment. We will also discuss additional challenges that must be overcome to produce state-of-the-art results. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/meetup11301-161207190211-thumbnail.jpg?width=120&height=120&fit=bounds" /> End-to-end speech recognition in Neon presented by Anthony Ndirango and Tyler Lee Modern automatic speech recognition systems incorporate tremendous amount of expert knowledge and a wide array of machine learning techniques. The promise of deep learning is to strip away much of this complexity in favor of the flexibility of neural networks. We will describe our efforts in implementing end-to-end speech recognition in neon by combining convolutional and recurrent neural networks to create an acoustic model followed by a graph-based decoding scheme. These types of models are trained to go directly from raw waveforms to transcribed speech without requiring any kind of explicit forced alignment. We will also discuss additional challenges that must be overcome to produce state-of-the-art results.

Intel Nervana Artificial Intelligence Meetup 11/30/16 from Intel Nervana

]]> 749 5 https://cdn.slidesharecdn.com/ss_thumbnails/meetup11301-161207190211-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 Learning at Scale /slideshow/deep-learning-at-scale/68608684 nervanareworknycv1-161110202746
Hanlin Tang presents at RE-Work NYC. He discusses Nervana's Deep Learning Platform.]]>
Hanlin Tang presents at RE-Work NYC. He discusses Nervana's Deep Learning Platform.]]> Thu, 10 Nov 2016 20:27:46 GMT /slideshow/deep-learning-at-scale/68608684 nervanasys@slideshare.net(nervanasys) Deep Learning at Scale nervanasys Hanlin Tang presents at RE-Work NYC. He discusses Nervana's Deep Learning Platform. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nervanareworknycv1-161110202746-thumbnail.jpg?width=120&height=120&fit=bounds" /> Hanlin Tang presents at RE-Work NYC. He discusses Nervana's Deep Learning Platform.

Deep Learning at Scale from Intel Nervana

]]> 1101 6 https://cdn.slidesharecdn.com/ss_thumbnails/nervanareworknycv1-161110202746-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 ODSC West /slideshow/odsc-west/68608585 nervanaodscmasterurs-161110202433
Urs Köster and Yinyin Liu present at ODSC West. Deep learning has had a major impact in the last three years. Imperfect interactions with machines, such as speech, natural language, or image processing have been made robust by deep learning and deep learning holds promise in finding usable structure in large datasets. The training process is lengthy and has proven to be difficult to scale due to constraints of existing compute architectures and there is a need of standardized tools for building and scaling deep learning solutions. Urs will outline some of these challenges and how fundamental changes to the organization of computation and communication can lead to large advances in capabilities. Urs will dive deep into the field of Deep Learning and focus on Convolutional and Recurrent Neural Networks. The talk will be followed by a workshop highlighting neon™, an open source python based deep learning framework that has been built from the ground up for speed and ease of use. This session is targeted at data scientists and researchers interested in taking deep learning to the next level of speed and scalability. The tutorial covers how to use neon™ to build and train Recurrent Neural Networks to generate text, and Convolutional Networks to perform image classification.]]>
Urs Köster and Yinyin Liu present at ODSC West. Deep learning has had a major impact in the last three years. Imperfect interactions with machines, such as speech, natural language, or image processing have been made robust by deep learning and deep learning holds promise in finding usable structure in large datasets. The training process is lengthy and has proven to be difficult to scale due to constraints of existing compute architectures and there is a need of standardized tools for building and scaling deep learning solutions. Urs will outline some of these challenges and how fundamental changes to the organization of computation and communication can lead to large advances in capabilities. Urs will dive deep into the field of Deep Learning and focus on Convolutional and Recurrent Neural Networks. The talk will be followed by a workshop highlighting neon™, an open source python based deep learning framework that has been built from the ground up for speed and ease of use. This session is targeted at data scientists and researchers interested in taking deep learning to the next level of speed and scalability. The tutorial covers how to use neon™ to build and train Recurrent Neural Networks to generate text, and Convolutional Networks to perform image classification.]]> Thu, 10 Nov 2016 20:24:32 GMT /slideshow/odsc-west/68608585 nervanasys@slideshare.net(nervanasys) ODSC West nervanasys Urs Köster and Yinyin Liu present at ODSC West. Deep learning has had a major impact in the last three years. Imperfect interactions with machines, such as speech, natural language, or image processing have been made robust by deep learning and deep learning holds promise in finding usable structure in large datasets. The training process is lengthy and has proven to be difficult to scale due to constraints of existing compute architectures and there is a need of standardized tools for building and scaling deep learning solutions. Urs will outline some of these challenges and how fundamental changes to the organization of computation and communication can lead to large advances in capabilities. Urs will dive deep into the field of Deep Learning and focus on Convolutional and Recurrent Neural Networks. The talk will be followed by a workshop highlighting neon™, an open source python based deep learning framework that has been built from the ground up for speed and ease of use. This session is targeted at data scientists and researchers interested in taking deep learning to the next level of speed and scalability. The tutorial covers how to use neon™ to build and train Recurrent Neural Networks to generate text, and Convolutional Networks to perform image classification. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nervanaodscmasterurs-161110202433-thumbnail.jpg?width=120&height=120&fit=bounds" /> Urs Köster and Yinyin Liu present at ODSC West. Deep learning has had a major impact in the last three years. Imperfect interactions with machines, such as speech, natural language, or image processing have been made robust by deep learning and deep learning holds promise in finding usable structure in large datasets. The training process is lengthy and has proven to be difficult to scale due to constraints of existing compute architectures and there is a need of standardized tools for building and scaling deep learning solutions. Urs will outline some of these challenges and how fundamental changes to the organization of computation and communication can lead to large advances in capabilities. Urs will dive deep into the field of Deep Learning and focus on Convolutional and Recurrent Neural Networks. The talk will be followed by a workshop highlighting neon™, an open source python based deep learning framework that has been built from the ground up for speed and ease of use. This session is targeted at data scientists and researchers interested in taking deep learning to the next level of speed and scalability. The tutorial covers how to use neon™ to build and train Recurrent Neural Networks to generate text, and Convolutional Networks to perform image classification.

ODSC West from Intel Nervana

]]> 542 4 https://cdn.slidesharecdn.com/ss_thumbnails/nervanaodscmasterurs-161110202433-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 Learning for Robotics /slideshow/deep-learning-for-robotics/68608405 nervanasdroboticsmeetup-161110202109
Yinyin Liu presents at SD Robotics Meetup on November 8th, 2016. Deep learning has made great success in image understanding, speech, text recognition and natural language processing. Deep Learning also has tremendous potential to tackle the challenges in robotic vision, and sensorimotor learning in a robotic learning environment. In this talk, we will talk about how current and future deep learning technologies can be applied for robotic applications. ]]>
Yinyin Liu presents at SD Robotics Meetup on November 8th, 2016. Deep learning has made great success in image understanding, speech, text recognition and natural language processing. Deep Learning also has tremendous potential to tackle the challenges in robotic vision, and sensorimotor learning in a robotic learning environment. In this talk, we will talk about how current and future deep learning technologies can be applied for robotic applications. ]]> Thu, 10 Nov 2016 20:21:09 GMT /slideshow/deep-learning-for-robotics/68608405 nervanasys@slideshare.net(nervanasys) Deep Learning for Robotics nervanasys Yinyin Liu presents at SD Robotics Meetup on November 8th, 2016. Deep learning has made great success in image understanding, speech, text recognition and natural language processing. Deep Learning also has tremendous potential to tackle the challenges in robotic vision, and sensorimotor learning in a robotic learning environment. In this talk, we will talk about how current and future deep learning technologies can be applied for robotic applications. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nervanasdroboticsmeetup-161110202109-thumbnail.jpg?width=120&height=120&fit=bounds" /> Yinyin Liu presents at SD Robotics Meetup on November 8th, 2016. Deep learning has made great success in image understanding, speech, text recognition and natural language processing. Deep Learning also has tremendous potential to tackle the challenges in robotic vision, and sensorimotor learning in a robotic learning environment. In this talk, we will talk about how current and future deep learning technologies can be applied for robotic applications.

Deep Learning for Robotics from Intel Nervana

]]> 1369 5 https://cdn.slidesharecdn.com/ss_thumbnails/nervanasdroboticsmeetup-161110202109-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 RE-Work Deep Learning Summit - September 2016 /slideshow/rework-deep-learning-summit-september-2016-66633733/66633733 rework-londonforpublicuse-160927222057-161001230859
Arjun Bansal presenting at RE-Work on Catalyzing Deep Learning's Impact in the Enterprise. ]]>
Arjun Bansal presenting at RE-Work on Catalyzing Deep Learning's Impact in the Enterprise. ]]> Sat, 01 Oct 2016 23:08:59 GMT /slideshow/rework-deep-learning-summit-september-2016-66633733/66633733 nervanasys@slideshare.net(nervanasys) RE-Work Deep Learning Summit - September 2016 nervanasys Arjun Bansal presenting at RE-Work on Catalyzing Deep Learning's Impact in the Enterprise. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/rework-londonforpublicuse-160927222057-161001230859-thumbnail.jpg?width=120&height=120&fit=bounds" /> Arjun Bansal presenting at RE-Work on Catalyzing Deep Learning's Impact in the Enterprise.

RE-Work Deep Learning Summit - September 2016 from Intel Nervana

]]> 451 2 https://cdn.slidesharecdn.com/ss_thumbnails/rework-londonforpublicuse-160927222057-161001230859-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 Using neon for pattern recognition in audio data /slideshow/using-neon-for-pattern-recognition-in-audio-data/64130245 audio-pattern-recognition-160718155653
Anil Thomas presents at Recurrent Neural Hacks Meetup on July 16, 2016. ]]>
Anil Thomas presents at Recurrent Neural Hacks Meetup on July 16, 2016. ]]> Mon, 18 Jul 2016 15:56:52 GMT /slideshow/using-neon-for-pattern-recognition-in-audio-data/64130245 nervanasys@slideshare.net(nervanasys) Using neon for pattern recognition in audio data nervanasys Anil Thomas presents at Recurrent Neural Hacks Meetup on July 16, 2016. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/audio-pattern-recognition-160718155653-thumbnail.jpg?width=120&height=120&fit=bounds" /> Anil Thomas presents at Recurrent Neural Hacks Meetup on July 16, 2016.

Using neon for pattern recognition in audio data from Intel Nervana

]]> 779 4 https://cdn.slidesharecdn.com/ss_thumbnails/audio-pattern-recognition-160718155653-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 An Analysis of Convolution for Inference /slideshow/an-analysis-of-convolution-for-inference/63427220 scottgrayicml2016-160624210604
Scott Gray presents at the 2016 ICML conference. Scott Gray went over various ways of computing convolution in the workshop on "On-device Intelligence". ]]>
Scott Gray presents at the 2016 ICML conference. Scott Gray went over various ways of computing convolution in the workshop on "On-device Intelligence". ]]> Fri, 24 Jun 2016 21:06:04 GMT /slideshow/an-analysis-of-convolution-for-inference/63427220 nervanasys@slideshare.net(nervanasys) An Analysis of Convolution for Inference nervanasys Scott Gray presents at the 2016 ICML conference. Scott Gray went over various ways of computing convolution in the workshop on "On-device Intelligence". <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/scottgrayicml2016-160624210604-thumbnail.jpg?width=120&height=120&fit=bounds" /> Scott Gray presents at the 2016 ICML conference. Scott Gray went over various ways of computing convolution in the workshop on "On-device Intelligence".

An Analysis of Convolution for Inference from Intel Nervana

]]> 6807 5 https://cdn.slidesharecdn.com/ss_thumbnails/scottgrayicml2016-160624210604-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 Rethinking computation: A processor architecture for machine intelligence /slideshow/rethinking-computation-a-processor-architecture-for-machine-intelligence/62240835 nfic2016-revised-160520204012
CTO of Nervana, Amir Khosrowshahi presents at New Frontiers in Computing 2016, Cognitive Computing: to the Singularity and Beyond at Stanford. ]]>
CTO of Nervana, Amir Khosrowshahi presents at New Frontiers in Computing 2016, Cognitive Computing: to the Singularity and Beyond at Stanford. ]]> Fri, 20 May 2016 20:40:12 GMT /slideshow/rethinking-computation-a-processor-architecture-for-machine-intelligence/62240835 nervanasys@slideshare.net(nervanasys) Rethinking computation: A processor architecture for machine intelligence nervanasys CTO of Nervana, Amir Khosrowshahi presents at New Frontiers in Computing 2016, Cognitive Computing: to the Singularity and Beyond at Stanford. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nfic2016-revised-160520204012-thumbnail.jpg?width=120&height=120&fit=bounds" /> CTO of Nervana, Amir Khosrowshahi presents at New Frontiers in Computing 2016, Cognitive Computing: to the Singularity and Beyond at Stanford.

Rethinking computation: A processor architecture for machine intelligence from Intel Nervana

]]> 1549 8 https://cdn.slidesharecdn.com/ss_thumbnails/nfic2016-revised-160520204012-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 Urs Köster Presenting at RE-Work DL Summit in Boston /nervanasys/urs-koster-presenting-at-rework-dl-summit-in-boston urs-rework2-160518175518
Deep Learning at Scale]]>
Deep Learning at Scale]]> Wed, 18 May 2016 17:55:18 GMT /nervanasys/urs-koster-presenting-at-rework-dl-summit-in-boston nervanasys@slideshare.net(nervanasys) Urs Köster Presenting at RE-Work DL Summit in Boston nervanasys Deep Learning at Scale <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/urs-rework2-160518175518-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep Learning at Scale

Urs K旦ster Presenting at RE-Work DL Summit in Boston from Intel Nervana

]]> 426 7 https://cdn.slidesharecdn.com/ss_thumbnails/urs-rework2-160518175518-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 Nervana and the Future of Computing /slideshow/nervana-and-the-future-of-computing/61473021 parismlmeetup-160428170722
Arjun Bansal speaks at Paris ML Meetup]]>
Arjun Bansal speaks at Paris ML Meetup]]> Thu, 28 Apr 2016 17:07:22 GMT /slideshow/nervana-and-the-future-of-computing/61473021 nervanasys@slideshare.net(nervanasys) Nervana and the Future of Computing nervanasys Arjun Bansal speaks at Paris ML Meetup <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/parismlmeetup-160428170722-thumbnail.jpg?width=120&height=120&fit=bounds" /> Arjun Bansal speaks at Paris ML Meetup

Nervana and the Future of Computing from Intel Nervana

]]> 1986 5 https://cdn.slidesharecdn.com/ss_thumbnails/parismlmeetup-160428170722-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 High-Performance GPU Programming for Deep Learning /slideshow/highperformance-gpu-programming-for-deep-learning/60884965 gtc2016-160413204442
This session goes over many of the techniques we use at Nervana in GPU programming to achieve state-of-the-art performance for deep learning networks. The main focus will be on the customization of dense linear algebra kernels: Winograd 3x3 convolution, direct convolution, and small tile GEMM (matrix multiply). In particular, we'll look at how we achieve high utilization at very small mini batches which is important for multi-gpu scaling and inference. In addition we'll talk about where and how you can effectively leverage lower and mixed precision to further increase performance without loss in accuracy.]]>
This session goes over many of the techniques we use at Nervana in GPU programming to achieve state-of-the-art performance for deep learning networks. The main focus will be on the customization of dense linear algebra kernels: Winograd 3x3 convolution, direct convolution, and small tile GEMM (matrix multiply). In particular, we'll look at how we achieve high utilization at very small mini batches which is important for multi-gpu scaling and inference. In addition we'll talk about where and how you can effectively leverage lower and mixed precision to further increase performance without loss in accuracy.]]> Wed, 13 Apr 2016 20:44:42 GMT /slideshow/highperformance-gpu-programming-for-deep-learning/60884965 nervanasys@slideshare.net(nervanasys) High-Performance GPU Programming for Deep Learning nervanasys This session goes over many of the techniques we use at Nervana in GPU programming to achieve state-of-the-art performance for deep learning networks. The main focus will be on the customization of dense linear algebra kernels: Winograd 3x3 convolution, direct convolution, and small tile GEMM (matrix multiply). In particular, we'll look at how we achieve high utilization at very small mini batches which is important for multi-gpu scaling and inference. In addition we'll talk about where and how you can effectively leverage lower and mixed precision to further increase performance without loss in accuracy. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gtc2016-160413204442-thumbnail.jpg?width=120&height=120&fit=bounds" /> This session goes over many of the techniques we use at Nervana in GPU programming to achieve state-of-the-art performance for deep learning networks. The main focus will be on the customization of dense linear algebra kernels: Winograd 3x3 convolution, direct convolution, and small tile GEMM (matrix multiply). In particular, we'll look at how we achieve high utilization at very small mini batches which is important for multi-gpu scaling and inference. In addition we'll talk about where and how you can effectively leverage lower and mixed precision to further increase performance without loss in accuracy.

High-Performance GPU Programming for Deep Learning from Intel Nervana

]]> 1820 4 https://cdn.slidesharecdn.com/ss_thumbnails/gtc2016-160413204442-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 Object Detection and Recognition /slideshow/object-detection-and-recognition/59094482 meetup03032016frcn-160304221312
Yinyin Liu presents a model for object detection and localization, called Fast-RCNN. She will show how to introduce a ROI pooling layer into neon, and how to add the PASCAL VOC dataset to interface with model training and inference. Lastly, Yinyin will run through a demo on how to apply the trained model to detect new objects. ]]>
Yinyin Liu presents a model for object detection and localization, called Fast-RCNN. She will show how to introduce a ROI pooling layer into neon, and how to add the PASCAL VOC dataset to interface with model training and inference. Lastly, Yinyin will run through a demo on how to apply the trained model to detect new objects. ]]> Fri, 04 Mar 2016 22:13:12 GMT /slideshow/object-detection-and-recognition/59094482 nervanasys@slideshare.net(nervanasys) Object Detection and Recognition nervanasys Yinyin Liu presents a model for object detection and localization, called Fast-RCNN. She will show how to introduce a ROI pooling layer into neon, and how to add the PASCAL VOC dataset to interface with model training and inference. Lastly, Yinyin will run through a demo on how to apply the trained model to detect new objects. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016frcn-160304221312-thumbnail.jpg?width=120&height=120&fit=bounds" /> Yinyin Liu presents a model for object detection and localization, called Fast-RCNN. She will show how to introduce a ROI pooling layer into neon, and how to add the PASCAL VOC dataset to interface with model training and inference. Lastly, Yinyin will run through a demo on how to apply the trained model to detect new objects.

Object Detection and Recognition from Intel Nervana

]]> 5165 6 https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016frcn-160304221312-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 Video Activity Recognition and NLP Q&A Model Example /slideshow/video-activity-recognition-and-nlp-qa-model-example/59092354 meetup03032016-1-160304205231
In this presentation, Sathish Nagappan will introduce the UCF-101 video activity recognition dataset and discuss how 3-D convolutions work. A demo will be presented on how to predict actions in video clips. Lastly, an NLP Q&A model example will be presented.]]>
In this presentation, Sathish Nagappan will introduce the UCF-101 video activity recognition dataset and discuss how 3-D convolutions work. A demo will be presented on how to predict actions in video clips. Lastly, an NLP Q&A model example will be presented.]]> Fri, 04 Mar 2016 20:52:30 GMT /slideshow/video-activity-recognition-and-nlp-qa-model-example/59092354 nervanasys@slideshare.net(nervanasys) Video Activity Recognition and NLP Q&A Model Example nervanasys In this presentation, Sathish Nagappan will introduce the UCF-101 video activity recognition dataset and discuss how 3-D convolutions work. A demo will be presented on how to predict actions in video clips. Lastly, an NLP Q&A model example will be presented. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016-1-160304205231-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this presentation, Sathish Nagappan will introduce the UCF-101 video activity recognition dataset and discuss how 3-D convolutions work. A demo will be presented on how to predict actions in video clips. Lastly, an NLP Q&A model example will be presented.

Video Activity Recognition and NLP Q&A Model Example from Intel Nervana

]]> 354 4 https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016-1-160304205231-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 Introduction to Deep Learning with Will Constable /slideshow/introduction-to-deep-learning-with-will-constable/59092288 meetup03032016-160304205016
Deep Residual Nets, Activity recognition in videos, and Q&A systems using neon and the Nervana Cloud Will Constable will start with an introduction to the field of Deep Learning, neon and the Nervana Cloud. The presentation will be followed by an interactive workshop using neon. neon is an open-source Python based Deep Learning framework that has been built from the ground up for speed, scalability and ease of use. ]]>
Deep Residual Nets, Activity recognition in videos, and Q&A systems using neon and the Nervana Cloud Will Constable will start with an introduction to the field of Deep Learning, neon and the Nervana Cloud. The presentation will be followed by an interactive workshop using neon. neon is an open-source Python based Deep Learning framework that has been built from the ground up for speed, scalability and ease of use. ]]> Fri, 04 Mar 2016 20:50:16 GMT /slideshow/introduction-to-deep-learning-with-will-constable/59092288 nervanasys@slideshare.net(nervanasys) Introduction to Deep Learning with Will Constable nervanasys Deep Residual Nets, Activity recognition in videos, and Q&A systems using neon and the Nervana Cloud Will Constable will start with an introduction to the field of Deep Learning, neon and the Nervana Cloud. The presentation will be followed by an interactive workshop using neon. neon is an open-source Python based Deep Learning framework that has been built from the ground up for speed, scalability and ease of use. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016-160304205016-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep Residual Nets, Activity recognition in videos, and Q&A systems using neon and the Nervana Cloud Will Constable will start with an introduction to the field of Deep Learning, neon and the Nervana Cloud. The presentation will be followed by an interactive workshop using neon. neon is an open-source Python based Deep Learning framework that has been built from the ground up for speed, scalability and ease of use.

Introduction to Deep Learning with Will Constable from Intel Nervana

]]> 771 4 https://cdn.slidesharecdn.com/ss_thumbnails/meetup03032016-160304205016-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 Startup.Ml: Using neon for NLP and Localization Applications /slideshow/startupml-using-neon-for-nlp-and-localization-applications/56708886 startupmlnov72015-160105181702
Speaker: Arjun Bansal, co-founder of Nervana Systems Arjun Bansal’s workshop focused on neon, an open-source python based deep learning framework that has been build from the ground up for speed and ease of use. The workshop highlights how to use neon, build Recurrent Recurrent Neural Networks to generate and analyze text, and build Convolutional Autoencoders to generate images and to localize objects. Arjun also demoed the integration of neon with the Nervana cloud (in private beta) for multi-GPU training of deep networks. ]]>
Speaker: Arjun Bansal, co-founder of Nervana Systems Arjun Bansal’s workshop focused on neon, an open-source python based deep learning framework that has been build from the ground up for speed and ease of use. The workshop highlights how to use neon, build Recurrent Recurrent Neural Networks to generate and analyze text, and build Convolutional Autoencoders to generate images and to localize objects. Arjun also demoed the integration of neon with the Nervana cloud (in private beta) for multi-GPU training of deep networks. ]]> Tue, 05 Jan 2016 18:17:02 GMT /slideshow/startupml-using-neon-for-nlp-and-localization-applications/56708886 nervanasys@slideshare.net(nervanasys) Startup.Ml: Using neon for NLP and Localization Applications nervanasys Speaker: Arjun Bansal, co-founder of Nervana Systems Arjun Bansal’s workshop focused on neon, an open-source python based deep learning framework that has been build from the ground up for speed and ease of use. The workshop highlights how to use neon, build Recurrent Recurrent Neural Networks to generate and analyze text, and build Convolutional Autoencoders to generate images and to localize objects. Arjun also demoed the integration of neon with the Nervana cloud (in private beta) for multi-GPU training of deep networks. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/startupmlnov72015-160105181702-thumbnail.jpg?width=120&height=120&fit=bounds" /> Speaker: Arjun Bansal, co-founder of Nervana Systems Arjun Bansal’s workshop focused on neon, an open-source python based deep learning framework that has been build from the ground up for speed and ease of use. The workshop highlights how to use neon, build Recurrent Recurrent Neural Networks to generate and analyze text, and build Convolutional Autoencoders to generate images and to localize objects. Arjun also demoed the integration of neon with the Nervana cloud (in private beta) for multi-GPU training of deep networks.

Startup.Ml: Using neon for NLP and Localization Applications from Intel Nervana

]]> 1468 9 https://cdn.slidesharecdn.com/ss_thumbnails/startupmlnov72015-160105181702-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://cdn.slidesharecdn.com/profile-photo-nervanasys-48x48.jpg?cb=1570084275 At Nervana, we are developing the next generation of solutions to tackle challenges in data analysis and computation. Using deep learning as a computational paradigm, we are optimizing from algorithms to hardware to develop intelligent solutions for real-world problems. Founded by experts in machine learning, neuroscience, and computer engineering, Nervana is bringing unprecedented scale and simplicity to these brain-inspired algorithms. nervanasys.com https://cdn.slidesharecdn.com/ss_thumbnails/galvanizedl-170530201913-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/introduction-to-deep-learning-and-neon-at-galvanize/76499620 Introduction to Deep L... https://cdn.slidesharecdn.com/ss_thumbnails/womeninaikickoffslidesall-170530201553-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/women-in-ai-kickoff/76499535 Women in AI kickoff https://cdn.slidesharecdn.com/ss_thumbnails/20170121startupmlconf-170201192357-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/intel-nervana-artificial-intelligence-meetup-13117/71651355 Intel Nervana Artifici...