Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor, CalTech
Anima Anandkumar is a principal scientist at Amazon Web Services and a Bren professor at Caltech CMS department. Her research interests are in the areas of large-scale machine learning, non-convex optimization and high-dimensional statistics. In particular, she has been spearheading the development and analysis of tensor algorithms. She is the recipient of several awards such as the Alfred. P. Sloan Fellowship, Microsoft Faculty Fellowship, Google research award, ARO and AFOSR Young Investigator Awards, NSF Career Award, Early Career Excellence in Research Award at UCI, Best Thesis Award from the ACM Sigmetrics society, IBM Fran Allen PhD fellowship, and several best paper awards. She has been featured in a number of forums such as the yourstory, Quora ML session, O’Reilly media, and so on. She received her B.Tech in Electrical Engineering from IIT Madras in 2004 and her PhD from Cornell University in 2009. She was a postdoctoral researcher at MIT from 2009 to 2010, an assistant professor at U.C. Irvine between 2010 and 2016, and a visiting researcher at Microsoft Research New England in 2012 and 2014.
Abstract Summary:
Large-scale Machine Learning: Deep, Distributed and Multi-Dimensional:
Modern machine learning involves deep neural network architectures which yields state-of-art performance on multiple domains such as computer vision, natural language processing and speech recognition. As the data and models scale, it becomes necessary to have multiple processing units for both training and inference. Apache MXNet is an open-source framework developed for distributed deep learning. I will describe the underlying lightweight hierarchical parameter server architecture that results in high efficiency in distributed settings.
Pushing the current boundaries of deep learning requires using multiple dimensions and modalities. These can be encoded into tensors, which are natural extensions of matrices. We present new deep learning architectures that preserve the multi-dimensional information in data end-to-end. We show that tensor contractions and regression layers are an effective replacement for fully connected layers in deep learning architectures. They result in significant space savings with negligible performance degradation. These functionalities are available in the Tensorly package with MXNet backend interface for large-scale efficient learning.
See Anima's slides here: https://www.slideshare.net/SessionsEvents/anima-anadkumar-principal-scientist-amazon-web-services-endowed-professor-caltech-at-mlconf-sf-2017
Видео Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor, CalTech канала MLconf
Abstract Summary:
Large-scale Machine Learning: Deep, Distributed and Multi-Dimensional:
Modern machine learning involves deep neural network architectures which yields state-of-art performance on multiple domains such as computer vision, natural language processing and speech recognition. As the data and models scale, it becomes necessary to have multiple processing units for both training and inference. Apache MXNet is an open-source framework developed for distributed deep learning. I will describe the underlying lightweight hierarchical parameter server architecture that results in high efficiency in distributed settings.
Pushing the current boundaries of deep learning requires using multiple dimensions and modalities. These can be encoded into tensors, which are natural extensions of matrices. We present new deep learning architectures that preserve the multi-dimensional information in data end-to-end. We show that tensor contractions and regression layers are an effective replacement for fully connected layers in deep learning architectures. They result in significant space savings with negligible performance degradation. These functionalities are available in the Tensorly package with MXNet backend interface for large-scale efficient learning.
See Anima's slides here: https://www.slideshare.net/SessionsEvents/anima-anadkumar-principal-scientist-amazon-web-services-endowed-professor-caltech-at-mlconf-sf-2017
Видео Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor, CalTech канала MLconf
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Jorge Silva, Sr. Research Statistician Developer, SAS @ MLconf ATL](https://i.ytimg.com/vi/uNMNJI9GsvQ/default.jpg)
![Dr. June Andrews, Principal Data Scientist, Wise.io, From GE Digital](https://i.ytimg.com/vi/8rQ9g03yJ8E/default.jpg)
![Building Machine Learning Models with Strict Privacy Boundaries](https://i.ytimg.com/vi/HIKpXVc1mpo/default.jpg)
![Manipulating and Measuring Model Interpretability](https://i.ytimg.com/vi/hHAW1ug2qlE/default.jpg)
![Jennifer Marsman, Principal Developer Evangelist, Microsoft @ MLconf NYC](https://i.ytimg.com/vi/T8FaWkqzK0A/default.jpg)
![MLconf Online 2020: DevOps for Data Science With Kubernetes by Sophie Watson](https://i.ytimg.com/vi/9TqHilvnUuM/default.jpg)
![Sven Kreiss, Lead Data Scientist, Wildcard @ MLconf ATL](https://i.ytimg.com/vi/09kpP-w4DLI/default.jpg)
![Virginia Smith - A General Framework for Communication-Efficient Distributed... - MLconf SF 2016](https://i.ytimg.com/vi/vuGiNJoq8NQ/default.jpg)
![Jeremy Stanley, EVP/Data Scientist, Sailthru @ MLconf NYC](https://i.ytimg.com/vi/vEemVVLGo6E/default.jpg)
![Sanjeev Satheesh, The Story of End to End Models in Deep Learning at The AI Conference 2017](https://i.ytimg.com/vi/h3Y3Gohn1HI/default.jpg)
![MLconf Online 2020: Data Science is Key to Achieving Energy Access in Africa Madeleine Gleave](https://i.ytimg.com/vi/i9FXqOeFpwY/default.jpg)
![Subutai Ahmad, VP of Research, Numenta @ MLconf SF](https://i.ytimg.com/vi/SxtsCrTHz-4/default.jpg)
![Justin Basilico, Senior Researcher Engineer in Recommendation Systems, Netlix @ MLconf ATL](https://i.ytimg.com/vi/doWgbo-c9sM/default.jpg)
![Ted Dunning, Chief Application Architect, MapR @ MLconf ATL](https://i.ytimg.com/vi/xTMdZPX8md0/default.jpg)
![MLconf Online 2020: Mathematical Approaches to Clustering by Joseph Ross](https://i.ytimg.com/vi/ziZ2JfXDAd4/default.jpg)
![Byron Galbraith, Chief Data Scientist, Talla, NYC 2017](https://i.ytimg.com/vi/IHCtfiI8llA/default.jpg)
![MLconf NYC 2022: How to Detect and Interpret Data Drift in Production by Emeli Dral of Evidently AI](https://i.ytimg.com/vi/FnVi_-eq4yE/default.jpg)
![Bryan Thompson, Chief Scientist and Founder, SYSTAP, LLC @ MLconf ATL](https://i.ytimg.com/vi/nUJvcLGXRuM/default.jpg)
![Optimized Image Classification on the Cheap](https://i.ytimg.com/vi/P5rU5LJfV5A/default.jpg)
![MLconf SF 2022: Essential Ingredients in Scaling Organizations for ML by Dr. Ali Arsanjani @Google](https://i.ytimg.com/vi/XwsTDUU93wc/default.jpg)