�ݺ�ߣshows by User: CyrusMoazamiVahid

�ݺ�ߣshows by User: CyrusMoazamiVahid / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: CyrusMoazamiVahid / Thu, 23 Aug 2018 13:32:03 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: CyrusMoazamiVahid Deep ar presentation /slideshow/deep-ar-presentation/111144653 deepar-presentation-180823133203
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.]]> Thu, 23 Aug 2018 13:32:03 GMT /slideshow/deep-ar-presentation/111144653 CyrusMoazamiVahid@slideshare.net(CyrusMoazamiVahid) Deep ar presentation CyrusMoazamiVahid 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/deepar-presentation-180823133203-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> 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.

Deep ar presentation from Cyrus Moazami-Vahid

]]> 1419 2 https://cdn.slidesharecdn.com/ss_thumbnails/deepar-presentation-180823133203-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 MXNet /CyrusMoazamiVahid/deep-learning-with-mxnet mxnetdl-180823132012
This deck quickly walks through fundamentals of Deep Learning and describes how symbolic engine of MXNet implements such networks. It then introduces gluon and provides code examples. The last section of the presentation introduces latest developments in gluon family of tools to include GluonNLP, an NLP toolkit with SOTA implementation of NLP algorithms, GluonCV, a Computer Vision toolkit with SOTA implementation of Vision algorithms, and MXNet backend for Keras.]]>
This deck quickly walks through fundamentals of Deep Learning and describes how symbolic engine of MXNet implements such networks. It then introduces gluon and provides code examples. The last section of the presentation introduces latest developments in gluon family of tools to include GluonNLP, an NLP toolkit with SOTA implementation of NLP algorithms, GluonCV, a Computer Vision toolkit with SOTA implementation of Vision algorithms, and MXNet backend for Keras.]]> Thu, 23 Aug 2018 13:20:12 GMT /CyrusMoazamiVahid/deep-learning-with-mxnet CyrusMoazamiVahid@slideshare.net(CyrusMoazamiVahid) Deep Learning with MXNet CyrusMoazamiVahid This deck quickly walks through fundamentals of Deep Learning and describes how symbolic engine of MXNet implements such networks. It then introduces gluon and provides code examples. The last section of the presentation introduces latest developments in gluon family of tools to include GluonNLP, an NLP toolkit with SOTA implementation of NLP algorithms, GluonCV, a Computer Vision toolkit with SOTA implementation of Vision algorithms, and MXNet backend for Keras. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mxnetdl-180823132012-thumbnail.jpg?width=120&height=120&fit=bounds" /><br> This deck quickly walks through fundamentals of Deep Learning and describes how symbolic engine of MXNet implements such networks. It then introduces gluon and provides code examples. The last section of the presentation introduces latest developments in gluon family of tools to include GluonNLP, an NLP toolkit with SOTA implementation of NLP algorithms, GluonCV, a Computer Vision toolkit with SOTA implementation of Vision algorithms, and MXNet backend for Keras.

Deep Learning with MXNet from Cyrus Moazami-Vahid

]]> 400 4 https://cdn.slidesharecdn.com/ss_thumbnails/mxnetdl-180823132012-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-CyrusMoazamiVahid-48x48.jpg?cb=1663187195 Cyrus is an AI specialist, proficient in Artificial Neural Networks and platforms such as Apache MXNet. He has been working on various stages of software development from Engineering to Leadership. His current interests include Natural Language processing, Recommender Systems, and Reinforcement Learning. https://cdn.slidesharecdn.com/ss_thumbnails/deepar-presentation-180823133203-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/deep-ar-presentation/111144653 Deep ar presentation https://cdn.slidesharecdn.com/ss_thumbnails/mxnetdl-180823132012-thumbnail.jpg?width=320&height=320&fit=bounds CyrusMoazamiVahid/deep-learning-with-mxnet Deep Learning with MXNet