�ݺ�ߣshows by User: apachemxnet

�ݺ�ߣshows by User: apachemxnet / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: apachemxnet / Mon, 07 Oct 2019 03:59:49 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: apachemxnet Recent Advances in Natural Language Processing /slideshow/recent-advances-in-natural-language-processing/179629621 naturallanguageprocessingadvances-191007035949
This talk goes over the recent progress made in the Natural Language Processing field in terms of Language Representation. Starting with the classic tf-idf, we cover word2vec, ELMo, BERT, GPT-2 and XL-Net. This deck was used for a ACNA2019 talk. �ݺ�ߣs: Thomas Delteil]]>
This talk goes over the recent progress made in the Natural Language Processing field in terms of Language Representation. Starting with the classic tf-idf, we cover word2vec, ELMo, BERT, GPT-2 and XL-Net. This deck was used for a ACNA2019 talk. �ݺ�ߣs: Thomas Delteil]]> Mon, 07 Oct 2019 03:59:49 GMT /slideshow/recent-advances-in-natural-language-processing/179629621 apachemxnet@slideshare.net(apachemxnet) Recent Advances in Natural Language Processing apachemxnet This talk goes over the recent progress made in the Natural Language Processing field in terms of Language Representation. Starting with the classic tf-idf, we cover word2vec, ELMo, BERT, GPT-2 and XL-Net. This deck was used for a ACNA2019 talk. �ݺ�ߣs: Thomas Delteil <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/naturallanguageprocessingadvances-191007035949-thumbnail.jpg?width=120&height=120&fit=bounds" /> This talk goes over the recent progress made in the Natural Language Processing field in terms of Language Representation. Starting with the classic tf-idf, we cover word2vec, ELMo, BERT, GPT-2 and XL-Net. This deck was used for a ACNA2019 talk. �ݺ�ߣs: Thomas Delteil

Recent Advances in Natural Language Processing from Apache MXNet

]]> 874 3 https://cdn.slidesharecdn.com/ss_thumbnails/naturallanguageprocessingadvances-191007035949-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 Fine-tuning BERT for Question Answering /slideshow/finetuning-bert-for-question-answering/179628340 questionansweringbert-191007035518
This deck covers the problem of fine-tuning a pre-trained BERT model for the task of Question Answering. Check out the GluonNLP model zoo here for models and tutorials: http://gluon-nlp.mxnet.io/model_zoo/bert/index.html �ݺ�ߣs: Thomas Delteil]]>
This deck covers the problem of fine-tuning a pre-trained BERT model for the task of Question Answering. Check out the GluonNLP model zoo here for models and tutorials: http://gluon-nlp.mxnet.io/model_zoo/bert/index.html �ݺ�ߣs: Thomas Delteil]]> Mon, 07 Oct 2019 03:55:18 GMT /slideshow/finetuning-bert-for-question-answering/179628340 apachemxnet@slideshare.net(apachemxnet) Fine-tuning BERT for Question Answering apachemxnet This deck covers the problem of fine-tuning a pre-trained BERT model for the task of Question Answering. Check out the GluonNLP model zoo here for models and tutorials: http://gluon-nlp.mxnet.io/model_zoo/bert/index.html �ݺ�ߣs: Thomas Delteil <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/questionansweringbert-191007035518-thumbnail.jpg?width=120&height=120&fit=bounds" /> This deck covers the problem of fine-tuning a pre-trained BERT model for the task of Question Answering. Check out the GluonNLP model zoo here for models and tutorials: http://gluon-nlp.mxnet.io/model_zoo/bert/index.html �ݺ�ߣs: Thomas Delteil

Fine-tuning BERT for Question Answering from Apache MXNet

]]> 3332 2 https://cdn.slidesharecdn.com/ss_thumbnails/questionansweringbert-191007035518-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 GluonNLP /slideshow/introduction-to-gluonnlp/179627690 introtogluonnlp-191007035322
GluonNLP is a deep learning toolkit for Natural Language Processing. These slides covers the motivation behind the creation of the toolkit and what is available in it. Go try it at https://gluon-nlp.mxnet.io! ]]>
GluonNLP is a deep learning toolkit for Natural Language Processing. These slides covers the motivation behind the creation of the toolkit and what is available in it. Go try it at https://gluon-nlp.mxnet.io! ]]> Mon, 07 Oct 2019 03:53:22 GMT /slideshow/introduction-to-gluonnlp/179627690 apachemxnet@slideshare.net(apachemxnet) Introduction to GluonNLP apachemxnet GluonNLP is a deep learning toolkit for Natural Language Processing. These slides covers the motivation behind the creation of the toolkit and what is available in it. Go try it at https://gluon-nlp.mxnet.io! <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/introtogluonnlp-191007035322-thumbnail.jpg?width=120&height=120&fit=bounds" /> GluonNLP is a deep learning toolkit for Natural Language Processing. These slides covers the motivation behind the creation of the toolkit and what is available in it. Go try it at https://gluon-nlp.mxnet.io!

Introduction to GluonNLP from Apache MXNet

]]> 124 3 https://cdn.slidesharecdn.com/ss_thumbnails/introtogluonnlp-191007035322-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 object tracking with Deep Learning /apachemxnet/introduction-to-object-tracking-with-deep-learning trackingwithdeeplearning-191007035109
This presentation introduces the problem of tracking object with deep learning and quickly go over specific implementations. Go build! https://mxnet.apache.org �ݺ�ߣs: Thomas Delteil]]>
This presentation introduces the problem of tracking object with deep learning and quickly go over specific implementations. Go build! https://mxnet.apache.org �ݺ�ߣs: Thomas Delteil]]> Mon, 07 Oct 2019 03:51:08 GMT /apachemxnet/introduction-to-object-tracking-with-deep-learning apachemxnet@slideshare.net(apachemxnet) Introduction to object tracking with Deep Learning apachemxnet This presentation introduces the problem of tracking object with deep learning and quickly go over specific implementations. Go build! https://mxnet.apache.org �ݺ�ߣs: Thomas Delteil <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/trackingwithdeeplearning-191007035109-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation introduces the problem of tracking object with deep learning and quickly go over specific implementations. Go build! https://mxnet.apache.org �ݺ�ߣs: Thomas Delteil

Introduction to object tracking with Deep Learning from Apache MXNet

]]> 7115 0 https://cdn.slidesharecdn.com/ss_thumbnails/trackingwithdeeplearning-191007035109-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 GluonCV /apachemxnet/introduction-to-gluoncv introtogluoncv-191007034813
Introduction to the deep learning Computer Vision toolkit GluonCV and the motivations behind its creation. Go try it! https://gluon-cv.mxnet.io ]]>
Introduction to the deep learning Computer Vision toolkit GluonCV and the motivations behind its creation. Go try it! https://gluon-cv.mxnet.io ]]> Mon, 07 Oct 2019 03:48:13 GMT /apachemxnet/introduction-to-gluoncv apachemxnet@slideshare.net(apachemxnet) Introduction to GluonCV apachemxnet Introduction to the deep learning Computer Vision toolkit GluonCV and the motivations behind its creation. Go try it! https://gluon-cv.mxnet.io <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/introtogluoncv-191007034813-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction to the deep learning Computer Vision toolkit GluonCV and the motivations behind its creation. Go try it! https://gluon-cv.mxnet.io

Introduction to GluonCV from Apache MXNet

]]> 329 3 https://cdn.slidesharecdn.com/ss_thumbnails/introtogluoncv-191007034813-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 Computer Vision /apachemxnet/introduction-to-computer-vision-179624949 introductiontocomputervision-191007034557
This presentation introduces the topic of computer vision, especially through the lense of Deep Learning. Go build! https://gluon-cv.mxnet.io �ݺ�ߣs: Thomas Delteil]]>
This presentation introduces the topic of computer vision, especially through the lense of Deep Learning. Go build! https://gluon-cv.mxnet.io �ݺ�ߣs: Thomas Delteil]]> Mon, 07 Oct 2019 03:45:56 GMT /apachemxnet/introduction-to-computer-vision-179624949 apachemxnet@slideshare.net(apachemxnet) Introduction to Computer Vision apachemxnet This presentation introduces the topic of computer vision, especially through the lense of Deep Learning. Go build! https://gluon-cv.mxnet.io �ݺ�ߣs: Thomas Delteil <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/introductiontocomputervision-191007034557-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation introduces the topic of computer vision, especially through the lense of Deep Learning. Go build! https://gluon-cv.mxnet.io �ݺ�ߣs: Thomas Delteil

Introduction to Computer Vision from Apache MXNet

]]> 112 0 https://cdn.slidesharecdn.com/ss_thumbnails/introductiontocomputervision-191007034557-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 Image Segmentation: Approaches and Challenges /slideshow/image-segmentation-approaches-and-challenges/179623840 imagesegmentationwithunet-191007034311
This slides go over the problem of deep semantic segmentation. It covers the different approaches taken, from hourglass autoencoder to pyramid networks. �ݺ�ߣs by Thomas Delteil]]>
This slides go over the problem of deep semantic segmentation. It covers the different approaches taken, from hourglass autoencoder to pyramid networks. �ݺ�ߣs by Thomas Delteil]]> Mon, 07 Oct 2019 03:43:11 GMT /slideshow/image-segmentation-approaches-and-challenges/179623840 apachemxnet@slideshare.net(apachemxnet) Image Segmentation: Approaches and Challenges apachemxnet This slides go over the problem of deep semantic segmentation. It covers the different approaches taken, from hourglass autoencoder to pyramid networks. �ݺ�ߣs by Thomas Delteil <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/imagesegmentationwithunet-191007034311-thumbnail.jpg?width=120&height=120&fit=bounds" /> This slides go over the problem of deep semantic segmentation. It covers the different approaches taken, from hourglass autoencoder to pyramid networks. �ݺ�ߣs by Thomas Delteil

Image Segmentation: Approaches and Challenges from Apache MXNet

]]> 260 1 https://cdn.slidesharecdn.com/ss_thumbnails/imagesegmentationwithunet-191007034311-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 face detection and recognition /apachemxnet/introduction-to-deep-face-detection-and-recognition facedetectionintro-191007033607
Deep Learning approaches tu face detection and recognition, state-of-art results and discussions of current limitations.]]>
Deep Learning approaches tu face detection and recognition, state-of-art results and discussions of current limitations.]]> Mon, 07 Oct 2019 03:36:07 GMT /apachemxnet/introduction-to-deep-face-detection-and-recognition apachemxnet@slideshare.net(apachemxnet) Introduction to Deep face detection and recognition apachemxnet Deep Learning approaches tu face detection and recognition, state-of-art results and discussions of current limitations. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/facedetectionintro-191007033607-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep Learning approaches tu face detection and recognition, state-of-art results and discussions of current limitations.

Introduction to Deep face detection and recognition from Apache MXNet

]]> 441 1 https://cdn.slidesharecdn.com/ss_thumbnails/facedetectionintro-191007033607-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 Generative Adversarial Networks (GANs) using Apache MXNet /slideshow/generative-adversarial-networks-gans-using-apache-mxnet-140380181/140380181 gan-190410211559
Introduction to AI and neural networks Introduction to CNNs Introduction to DCGAN with code demo]]>
Introduction to AI and neural networks Introduction to CNNs Introduction to DCGAN with code demo]]> Wed, 10 Apr 2019 21:15:59 GMT /slideshow/generative-adversarial-networks-gans-using-apache-mxnet-140380181/140380181 apachemxnet@slideshare.net(apachemxnet) Generative Adversarial Networks (GANs) using Apache MXNet apachemxnet Introduction to AI and neural networks Introduction to CNNs Introduction to DCGAN with code demo <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gan-190410211559-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction to AI and neural networks Introduction to CNNs Introduction to DCGAN with code demo

Generative Adversarial Networks (GANs) using Apache MXNet from Apache MXNet

]]> 386 9 https://cdn.slidesharecdn.com/ss_thumbnails/gan-190410211559-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 With Apache MXNet On Video by Ben Taylor @ ziff.ai /slideshow/deep-learning-with-apache-mxnet-on-video-by-ben-taylor-ziffai/138340572 amazonmeetuppresentation-190326231239
This talk will go over using Apache MXNet on video streams such as security footage from Ring, or live XBOX video data to perform inference and indexing. This can be used to classify video events, detect anomalies in normal behavior, and search. This talk will focus on using FFMPEG for feeding Apache MXNet models for fast inference throughput and performance. This talk will also discuss the difference between frame level inference, and frame buffer inference (comprehending a temporal video event). Links to videos on the slides: IntelAct: Winner, Visual Doom AI Competition, Full Deathmatch: https://www.youtube.com/watch?v=947bSUtuSQ0 GPU assisted call of duty processing, prep for AI auto-play: https://www.youtube.com/watch?v=gTXOYzSC_ZE Presented at https://www.meetup.com/deep-learning-with-mxnet/events/258901722/ ]]>
This talk will go over using Apache MXNet on video streams such as security footage from Ring, or live XBOX video data to perform inference and indexing. This can be used to classify video events, detect anomalies in normal behavior, and search. This talk will focus on using FFMPEG for feeding Apache MXNet models for fast inference throughput and performance. This talk will also discuss the difference between frame level inference, and frame buffer inference (comprehending a temporal video event). Links to videos on the slides: IntelAct: Winner, Visual Doom AI Competition, Full Deathmatch: https://www.youtube.com/watch?v=947bSUtuSQ0 GPU assisted call of duty processing, prep for AI auto-play: https://www.youtube.com/watch?v=gTXOYzSC_ZE Presented at https://www.meetup.com/deep-learning-with-mxnet/events/258901722/ ]]> Tue, 26 Mar 2019 23:12:39 GMT /slideshow/deep-learning-with-apache-mxnet-on-video-by-ben-taylor-ziffai/138340572 apachemxnet@slideshare.net(apachemxnet) Deep Learning With Apache MXNet On Video by Ben Taylor @ ziff.ai apachemxnet This talk will go over using Apache MXNet on video streams such as security footage from Ring, or live XBOX video data to perform inference and indexing. This can be used to classify video events, detect anomalies in normal behavior, and search. This talk will focus on using FFMPEG for feeding Apache MXNet models for fast inference throughput and performance. This talk will also discuss the difference between frame level inference, and frame buffer inference (comprehending a temporal video event). Links to videos on the slides: IntelAct: Winner, Visual Doom AI Competition, Full Deathmatch: https://www.youtube.com/watch?v=947bSUtuSQ0 GPU assisted call of duty processing, prep for AI auto-play: https://www.youtube.com/watch?v=gTXOYzSC_ZE Presented at https://www.meetup.com/deep-learning-with-mxnet/events/258901722/ <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/amazonmeetuppresentation-190326231239-thumbnail.jpg?width=120&height=120&fit=bounds" /> This talk will go over using Apache MXNet on video streams such as security footage from Ring, or live XBOX video data to perform inference and indexing. This can be used to classify video events, detect anomalies in normal behavior, and search. This talk will focus on using FFMPEG for feeding Apache MXNet models for fast inference throughput and performance. This talk will also discuss the difference between frame level inference, and frame buffer inference (comprehending a temporal video event). Links to videos on the slides: IntelAct: Winner, Visual Doom AI Competition, Full Deathmatch: https://www.youtube.com/watch?v=947bSUtuSQ0 GPU assisted call of duty processing, prep for AI auto-play: https://www.youtube.com/watch?v=gTXOYzSC_ZE Presented at https://www.meetup.com/deep-learning-with-mxnet/events/258901722/

Deep Learning With Apache MXNet On Video by Ben Taylor @ ziff.ai from Apache MXNet

]]> 204 4 https://cdn.slidesharecdn.com/ss_thumbnails/amazonmeetuppresentation-190326231239-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 Java to deploy Deep Learning models with MXNet /slideshow/using-java-to-deploy-deep-learning-models-with-mxnet/133227225 apachemxnetjavameetup-190225144706
Using Java for deploying Deep Learning models with Apache MXNet]]>
Using Java for deploying Deep Learning models with Apache MXNet]]> Mon, 25 Feb 2019 14:47:06 GMT /slideshow/using-java-to-deploy-deep-learning-models-with-mxnet/133227225 apachemxnet@slideshare.net(apachemxnet) Using Java to deploy Deep Learning models with MXNet apachemxnet Using Java for deploying Deep Learning models with Apache MXNet <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/apachemxnetjavameetup-190225144706-thumbnail.jpg?width=120&height=120&fit=bounds" /> Using Java for deploying Deep Learning models with Apache MXNet

Using Java to deploy Deep Learning models with MXNet from Apache MXNet

]]> 303 2 https://cdn.slidesharecdn.com/ss_thumbnails/apachemxnetjavameetup-190225144706-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 AI powered emotion recognition: From Inception to Production - Global AI Conference 2019 /apachemxnet/ai-powered-emotion-recognition-from-inception-to-production-global-ai-conference-2019 gaic2019-sc-190125214638
Introduction to Deep Learning, Handwritten digit recognition - MLP Example Facial Emotion Recognition - CNN, Transfer learning MXNet Model Server]]>
Introduction to Deep Learning, Handwritten digit recognition - MLP Example Facial Emotion Recognition - CNN, Transfer learning MXNet Model Server]]> Fri, 25 Jan 2019 21:46:38 GMT /apachemxnet/ai-powered-emotion-recognition-from-inception-to-production-global-ai-conference-2019 apachemxnet@slideshare.net(apachemxnet) AI powered emotion recognition: From Inception to Production - Global AI Conference 2019 apachemxnet Introduction to Deep Learning, Handwritten digit recognition - MLP Example Facial Emotion Recognition - CNN, Transfer learning MXNet Model Server <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gaic2019-sc-190125214638-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction to Deep Learning, Handwritten digit recognition - MLP Example Facial Emotion Recognition - CNN, Transfer learning MXNet Model Server

AI powered emotion recognition: From Inception to Production - Global AI Conference 2019 from Apache MXNet

]]> 254 13 https://cdn.slidesharecdn.com/ss_thumbnails/gaic2019-sc-190125214638-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 MXNet Paris Workshop - Intro To MXNet /apachemxnet/mxnet-paris-workshop-intro-to-mxnet mxnetcompact2019-01-08-190110111946
MXNet Paris Workshop - Intro To MXNet]]>
MXNet Paris Workshop - Intro To MXNet]]> Thu, 10 Jan 2019 11:19:46 GMT /apachemxnet/mxnet-paris-workshop-intro-to-mxnet apachemxnet@slideshare.net(apachemxnet) MXNet Paris Workshop - Intro To MXNet apachemxnet MXNet Paris Workshop - Intro To MXNet <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mxnetcompact2019-01-08-190110111946-thumbnail.jpg?width=120&height=120&fit=bounds" /> MXNet Paris Workshop - Intro To MXNet

MXNet Paris Workshop - Intro To MXNet from Apache MXNet

]]> 326 4 https://cdn.slidesharecdn.com/ss_thumbnails/mxnetcompact2019-01-08-190110111946-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 Apache MXNet ODSC West 2018 /apachemxnet/apache-mxnet-odsc-west-2018 odsc2018-sf-181102174953
Deep Learning using Apache MXNet ]]>
Deep Learning using Apache MXNet ]]> Fri, 02 Nov 2018 17:49:53 GMT /apachemxnet/apache-mxnet-odsc-west-2018 apachemxnet@slideshare.net(apachemxnet) Apache MXNet ODSC West 2018 apachemxnet Deep Learning using Apache MXNet <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/odsc2018-sf-181102174953-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep Learning using Apache MXNet

Apache MXNet ODSC West 2018 from Apache MXNet

]]> 227 5 https://cdn.slidesharecdn.com/ss_thumbnails/odsc2018-sf-181102174953-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 DeepLearning001&ApacheMXNetWithSparkForInference-ACNA2018 /slideshow/deeplearning001apachemxnetwithsparkforinferenceacna2018/117346123 deeplearning001mxnetwithspark-acna2018-180929155046
What is Deep Learning Rise of Deep Learning Phases of Deep Learning - Training and Inference AI & Limitations of Deep Learning Apache MXNet History, Apache MXNet concepts How to use Apache MXNet and Spark together for Distributed Inference.]]>
What is Deep Learning Rise of Deep Learning Phases of Deep Learning - Training and Inference AI & Limitations of Deep Learning Apache MXNet History, Apache MXNet concepts How to use Apache MXNet and Spark together for Distributed Inference.]]> Sat, 29 Sep 2018 15:50:46 GMT /slideshow/deeplearning001apachemxnetwithsparkforinferenceacna2018/117346123 apachemxnet@slideshare.net(apachemxnet) DeepLearning001&ApacheMXNetWithSparkForInference-ACNA2018 apachemxnet What is Deep Learning Rise of Deep Learning Phases of Deep Learning - Training and Inference AI & Limitations of Deep Learning Apache MXNet History, Apache MXNet concepts How to use Apache MXNet and Spark together for Distributed Inference. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/deeplearning001mxnetwithspark-acna2018-180929155046-thumbnail.jpg?width=120&height=120&fit=bounds" /> What is Deep Learning Rise of Deep Learning Phases of Deep Learning - Training and Inference AI & Limitations of Deep Learning Apache MXNet History, Apache MXNet concepts How to use Apache MXNet and Spark together for Distributed Inference.

DeepLearning001&ApacheMXNetWithSparkForInference-ACNA2018 from Apache MXNet

]]> 123 3 https://cdn.slidesharecdn.com/ss_thumbnails/deeplearning001mxnetwithspark-acna2018-180929155046-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 Apache MXNet EcoSystem - ACNA2018 /slideshow/apache-mxnet-ecosystem-acna2018/117344691 apachemxnetecosystem-acna2018-180929153931
Various Open Source projects around Apache MXNet for you to build End to End pipeline from building Models using 7 different languages to choose from or use Keras if you are already a Keras user. Get the state of the Art models pre-trained with code and examples using GluonCV and GluonNLP Use ONNX to create and save models right from MXNet so you can port to any framework. Use Apache 2.0 Licensed MXNet Model Server to deploy your models. Use TVM to optimize for your own hardware.]]>
Various Open Source projects around Apache MXNet for you to build End to End pipeline from building Models using 7 different languages to choose from or use Keras if you are already a Keras user. Get the state of the Art models pre-trained with code and examples using GluonCV and GluonNLP Use ONNX to create and save models right from MXNet so you can port to any framework. Use Apache 2.0 Licensed MXNet Model Server to deploy your models. Use TVM to optimize for your own hardware.]]> Sat, 29 Sep 2018 15:39:31 GMT /slideshow/apache-mxnet-ecosystem-acna2018/117344691 apachemxnet@slideshare.net(apachemxnet) Apache MXNet EcoSystem - ACNA2018 apachemxnet Various Open Source projects around Apache MXNet for you to build End to End pipeline from building Models using 7 different languages to choose from or use Keras if you are already a Keras user. Get the state of the Art models pre-trained with code and examples using GluonCV and GluonNLP Use ONNX to create and save models right from MXNet so you can port to any framework. Use Apache 2.0 Licensed MXNet Model Server to deploy your models. Use TVM to optimize for your own hardware. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/apachemxnetecosystem-acna2018-180929153931-thumbnail.jpg?width=120&height=120&fit=bounds" /> Various Open Source projects around Apache MXNet for you to build End to End pipeline from building Models using 7 different languages to choose from or use Keras if you are already a Keras user. Get the state of the Art models pre-trained with code and examples using GluonCV and GluonNLP Use ONNX to create and save models right from MXNet so you can port to any framework. Use Apache 2.0 Licensed MXNet Model Server to deploy your models. Use TVM to optimize for your own hardware.

Apache MXNet EcoSystem - ACNA2018 from Apache MXNet

]]> 410 3 https://cdn.slidesharecdn.com/ss_thumbnails/apachemxnetecosystem-acna2018-180929153931-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 ONNX and Edge Deployments /slideshow/onnx-and-edge-deployments/115815828 onnxtoedgefinal-180921170321
In this talk ONNX (Open Neural Network eXchange) is introduced, and the ONNX Model Zoo is used as the base for fine-tuning with AWS SageMaker and Apache MXNet's Gluon API. With a fine-tuned model trained on Caltech101, AWS GreenGrass is discussed for edge deployments and the TVM Stack is suggested as a method for optimising the inference of models on edge devices. Presented by: Thom Lane at Linaro Connect Vancouver 2018 on 19th September 2018.]]>
In this talk ONNX (Open Neural Network eXchange) is introduced, and the ONNX Model Zoo is used as the base for fine-tuning with AWS SageMaker and Apache MXNet's Gluon API. With a fine-tuned model trained on Caltech101, AWS GreenGrass is discussed for edge deployments and the TVM Stack is suggested as a method for optimising the inference of models on edge devices. Presented by: Thom Lane at Linaro Connect Vancouver 2018 on 19th September 2018.]]> Fri, 21 Sep 2018 17:03:21 GMT /slideshow/onnx-and-edge-deployments/115815828 apachemxnet@slideshare.net(apachemxnet) ONNX and Edge Deployments apachemxnet In this talk ONNX (Open Neural Network eXchange) is introduced, and the ONNX Model Zoo is used as the base for fine-tuning with AWS SageMaker and Apache MXNet's Gluon API. With a fine-tuned model trained on Caltech101, AWS GreenGrass is discussed for edge deployments and the TVM Stack is suggested as a method for optimising the inference of models on edge devices. Presented by: Thom Lane at Linaro Connect Vancouver 2018 on 19th September 2018. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/onnxtoedgefinal-180921170321-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this talk ONNX (Open Neural Network eXchange) is introduced, and the ONNX Model Zoo is used as the base for fine-tuning with AWS SageMaker and Apache MXNet's Gluon API. With a fine-tuned model trained on Caltech101, AWS GreenGrass is discussed for edge deployments and the TVM Stack is suggested as a method for optimising the inference of models on edge devices. Presented by: Thom Lane at Linaro Connect Vancouver 2018 on 19th September 2018.

ONNX and Edge Deployments from Apache MXNet

]]> 362 2 https://cdn.slidesharecdn.com/ss_thumbnails/onnxtoedgefinal-180921170321-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 Distributed Inference with MXNet and Spark /slideshow/distributed-inference-with-mxnet-and-spark-114142976/114142976 mxnet-sparkslides-180912210017
Deep Learning has become ubiquitous with abundance of data, commoditization of compute and storage. Pre-trained models are readily available for many use-cases. Distributed Inference has many applications such as pre-computing results offline, backfilling historic data with predictions from state-of-the-art models, etc.,. Inference on large scale datasets comes with many challenges prevalent in distributed data processing. This presentation will show how to efficiently run deep learning prediction on large data sets, leveraging Apache Spark and Apache MXNet (incubating).]]>
Deep Learning has become ubiquitous with abundance of data, commoditization of compute and storage. Pre-trained models are readily available for many use-cases. Distributed Inference has many applications such as pre-computing results offline, backfilling historic data with predictions from state-of-the-art models, etc.,. Inference on large scale datasets comes with many challenges prevalent in distributed data processing. This presentation will show how to efficiently run deep learning prediction on large data sets, leveraging Apache Spark and Apache MXNet (incubating).]]> Wed, 12 Sep 2018 21:00:17 GMT /slideshow/distributed-inference-with-mxnet-and-spark-114142976/114142976 apachemxnet@slideshare.net(apachemxnet) Distributed Inference with MXNet and Spark apachemxnet Deep Learning has become ubiquitous with abundance of data, commoditization of compute and storage. Pre-trained models are readily available for many use-cases. Distributed Inference has many applications such as pre-computing results offline, backfilling historic data with predictions from state-of-the-art models, etc.,. Inference on large scale datasets comes with many challenges prevalent in distributed data processing. This presentation will show how to efficiently run deep learning prediction on large data sets, leveraging Apache Spark and Apache MXNet (incubating). <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mxnet-sparkslides-180912210017-thumbnail.jpg?width=120&height=120&fit=bounds" /> Deep Learning has become ubiquitous with abundance of data, commoditization of compute and storage. Pre-trained models are readily available for many use-cases. Distributed Inference has many applications such as pre-computing results offline, backfilling historic data with predictions from state-of-the-art models, etc.,. Inference on large scale datasets comes with many challenges prevalent in distributed data processing. This presentation will show how to efficiently run deep learning prediction on large data sets, leveraging Apache Spark and Apache MXNet (incubating).

Distributed Inference with MXNet and Spark from Apache MXNet

]]> 131 1 https://cdn.slidesharecdn.com/ss_thumbnails/mxnet-sparkslides-180912210017-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 Multivariate Time Series /slideshow/multivariate-time-series-111359256/111359256 time-series-180824184812
This presentation describes two major papers in multi-variate time-series using deep neural networks. The first paper, DeepAR was developed at Amazon to deal with forecasting of millions of items where the same model can be applied to millions of products. DeepAR is implemented as a built-in algorithm of Amazon SageMaker. Code example is provided. The second paper, Long- and Short-Term Temporal Patterns with Deep Neural Networks is developed at CMU and introduces a novel way to detect both short term and long term seasonality in data through introduction of skip-rnn. A Gluon implementation of the paper is provided in the presentation.]]>
This presentation describes two major papers in multi-variate time-series using deep neural networks. The first paper, DeepAR was developed at Amazon to deal with forecasting of millions of items where the same model can be applied to millions of products. DeepAR is implemented as a built-in algorithm of Amazon SageMaker. Code example is provided. The second paper, Long- and Short-Term Temporal Patterns with Deep Neural Networks is developed at CMU and introduces a novel way to detect both short term and long term seasonality in data through introduction of skip-rnn. A Gluon implementation of the paper is provided in the presentation.]]> Fri, 24 Aug 2018 18:48:12 GMT /slideshow/multivariate-time-series-111359256/111359256 apachemxnet@slideshare.net(apachemxnet) Multivariate Time Series apachemxnet This presentation describes two major papers in multi-variate time-series using deep neural networks. The first paper, DeepAR was developed at Amazon to deal with forecasting of millions of items where the same model can be applied to millions of products. DeepAR is implemented as a built-in algorithm of Amazon SageMaker. Code example is provided. The second paper, Long- and Short-Term Temporal Patterns with Deep Neural Networks is developed at CMU and introduces a novel way to detect both short term and long term seasonality in data through introduction of skip-rnn. A Gluon implementation of the paper is provided in the presentation. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/time-series-180824184812-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation describes two major papers in multi-variate time-series using deep neural networks. The first paper, DeepAR was developed at Amazon to deal with forecasting of millions of items where the same model can be applied to millions of products. DeepAR is implemented as a built-in algorithm of Amazon SageMaker. Code example is provided. The second paper, Long- and Short-Term Temporal Patterns with Deep Neural Networks is developed at CMU and introduces a novel way to detect both short term and long term seasonality in data through introduction of skip-rnn. A Gluon implementation of the paper is provided in the presentation.

Multivariate Time Series from Apache MXNet

]]> 633 2 https://cdn.slidesharecdn.com/ss_thumbnails/time-series-180824184812-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 AI On the Edge: Model Compression /apachemxnet/ai-on-the-edge-model-compression modelcompression-180824184016
Inference on edge has an ever increasing performance for companies and thus it is crucial to be able to make models smaller. Compressing models can be loss-less or can result in loss of accuracy. This presentation provides a survey of compression techniques for deep learning models. It then describes different architectures of AWS IoT/Green Grass to combine on-device inference and GPU inference in a hub model. Additionally the presentation introduces MXNet, which has small footprint and efficient both for inference and training in distributed settings.]]>
Inference on edge has an ever increasing performance for companies and thus it is crucial to be able to make models smaller. Compressing models can be loss-less or can result in loss of accuracy. This presentation provides a survey of compression techniques for deep learning models. It then describes different architectures of AWS IoT/Green Grass to combine on-device inference and GPU inference in a hub model. Additionally the presentation introduces MXNet, which has small footprint and efficient both for inference and training in distributed settings.]]> Fri, 24 Aug 2018 18:40:16 GMT /apachemxnet/ai-on-the-edge-model-compression apachemxnet@slideshare.net(apachemxnet) AI On the Edge: Model Compression apachemxnet Inference on edge has an ever increasing performance for companies and thus it is crucial to be able to make models smaller. Compressing models can be loss-less or can result in loss of accuracy. This presentation provides a survey of compression techniques for deep learning models. It then describes different architectures of AWS IoT/Green Grass to combine on-device inference and GPU inference in a hub model. Additionally the presentation introduces MXNet, which has small footprint and efficient both for inference and training in distributed settings. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/modelcompression-180824184016-thumbnail.jpg?width=120&height=120&fit=bounds" /> Inference on edge has an ever increasing performance for companies and thus it is crucial to be able to make models smaller. Compressing models can be loss-less or can result in loss of accuracy. This presentation provides a survey of compression techniques for deep learning models. It then describes different architectures of AWS IoT/Green Grass to combine on-device inference and GPU inference in a hub model. Additionally the presentation introduces MXNet, which has small footprint and efficient both for inference and training in distributed settings.

AI On the Edge: Model Compression from Apache MXNet

]]> 580 5 https://cdn.slidesharecdn.com/ss_thumbnails/modelcompression-180824184016-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-apachemxnet-48x48.jpg?cb=1570419277 Open source, scalable deep-learning engine. mxnet.incubator.apache.org https://cdn.slidesharecdn.com/ss_thumbnails/naturallanguageprocessingadvances-191007035949-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/recent-advances-in-natural-language-processing/179629621 Recent Advances in Nat... https://cdn.slidesharecdn.com/ss_thumbnails/questionansweringbert-191007035518-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/finetuning-bert-for-question-answering/179628340 Fine-tuning BERT for Q... https://cdn.slidesharecdn.com/ss_thumbnails/introtogluonnlp-191007035322-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/introduction-to-gluonnlp/179627690 Introduction to GluonNLP