Ushering in the Era of Programmable Hardware
Deep learning enables large-scale computer image recognition with Project Adam
Download this episode
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
Format
Available formats for this video:
Actual format may change based on video formats available and browser capability.
More episodes in this series
John Platt on AI, Cortana, and Project Adam
Related episodes
Idea Date Science - Session 1
Artificial Intelligence to Ease Parents' Pain in Summer Camp Planning
Machine Learning from Verbal Instruction
Universally Scalable Concurrent Search Data Structures
Sentiment and Emotion Analysis for Social Multimedia: Methodologies and Applications
DISCO Nets: DIssimilarity COefficient Networks
Grammar Variational Autoencoder
Bayesian optimisation in many dimensions with bespoke models
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
The Supervised Word Mover's Distance
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 ?
Comments closed
Comments have been closed since this content was published more than 30 days ago, but if you'd like to send us feedback you can Contact Us.