Skip to yearly menu bar Skip to main content


Talk

AdaNet: Adaptive Structural Learning of Artificial Neural Networks

Corinna Cortes · Xavi Gonzalvo · Vitaly Kuznetsov · Mehryar Mohri · Scott Yang

[ ]
[ PDF [ ss Summary/Notes [ Video
2017 Talk

Abstract:

We present a new framework for analyzing and learning artificial neural networks. Our approach simultaneously and adaptively learns both the structure of the network as well as its weights. The methodology is based upon and accompanied by strong data-dependent theoretical learning guarantees, so that the final network architecture provably adapts to the complexity of any given problem.

Chat is not available.