Geometric Intuition for Training Neural Networks

By Leo Dirac. From Sea-ADL’s first meetup on November 12, 2019, hosted by Moz.

Leo Dirac explains what it looks like to train a neural network through geometric intuition. The structure of the talk is:

  • Supervised learning. What does a decision boundary look for a simple binary classification problem, and how do the data interact with it during the training process. What is a loss surface, and how does SGD find its way to the bottom of it.
  • Training Deep Neural Networks with Non-Convex Optimization. How neural networks make the decision boundary more complex, and what a non-convex loss surface looks like. Then some recent research into the shapes of these loss surfaces, starting with how the sharp minima theory implies we should seek a wide valley in the loss surface. Then research implying that all local minima are equivalent and connected, and a couple of algorithms including Entropy-SGD and SWA to take advantage of this structure.
  • Practical applications with Code. Code samples showing how to apply SWA using PyTorch or TensorFlow.

Published by seaadl

We're a new community for tech professionals applying AI to solve real world problems.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: