Machine Learning w. Neural Nets
Instructor: Dr. Mike Bowles
599 Fairchild Drive
Mountain View, CA
Also available live by video conference
Class will meet for 8 sessions on Wed and Thurs evenings from 7:00 to 9:00 pm.
First meeting: Wed Mar 27th from 7:00 – 9:00 pm
Neural nets were officially pronounced dead in the 90’s, but Canadian scholars didn’t get the memo. Their thoughtful, persistence has lead to several new discoveries that have resurrected neural nets and made them the best choice for a number of extremely difficult problems like speech recognition and handwriting recognition. (Geoffrey Hinton, one of the leading Canadian scholars just announced that he’s coming to Google. https://plus.google.com/u/0/102889418997957626067/posts/GWe4AscQdS7 )
This course will cover background on neural nets, their origins, traditional architectures and recent developments such as auto-encoders and restricted Boltzman machines.
Some of the Neural Net Topics that we’ll cover
Intro to Neural Nets
Recurrent neural nets
How to regularize neural nets
Deep belief nets
The class will undergraduate level calculus and linear algebra and moderate programming skills. We’ll use R and Python primarily. Some familiarity with machine learning problems (e.g. linear regression) will be helpful, but not strictly required.
For more info:
Registration for the Class (all 8 meetings)