Ushering in the Era of Programmable Hardware
Deep learning enables large-scale computer image recognition with Project Adam
Description
Trishul Chilimbi, Partner Research Manager for Microsoft Research, discusses Project Adam, and how deep neural networks have enabled large-scale computer image recognition with astounding accuracy.
Share
Download
Download this episode
- MP3 (12.7 MB)
- Low Quality MP4 (34.8 MB)
- High Quality MP4 (426.6 MB)
- Mid Quality MP4 (137.3 MB)
More episodes in this series
John Platt on AI, Cortana, and Project Adam
Related episodes
Small Deep Neural Networks - Their Advantages, and Their Design
Constrained Temporal Variation in Speech
Trading-Off Cost of Deployment Versus Accuracy for Predictive Models
Articulated Human Pose Tracking with Inertial Sensors
Fundamentals of User Studies
Social Network Analysis
Automatic Speech Recognition - An Overview
Computational Pragmatics
Multilingualism
NLP for Social Media
The Discussion
-
Jeff Petty Amazing. Lover the reference to the potential for blind people. Clear accessibility applications and an opportunity to differentiate Microsoft. Be sure to connect with the folks in Trustworthy Computing.
-
Niner807642 Nice video! I like the possibilities and it is even at this state (dog recognition) amazing... what I am interested in: will adam feed the Backend of Cortanan/bimg, will he learn from it? Or is it currently doing already.
Thanks!
-
briankel Larry, are you suggesting that a horse isn't just a big dog?
-
Jules Really keen to know when we can get hold of this MS Machine learning Framework, on Azure. Surely Microsoft can provide an Azure Services of Images and Meta Data [Training Set] into an Azure hosted Framework, to allow us developers to play with this neural net technology ?