Introduction to Feedforward Neural Networks

Casey Kennington
1:40-2:55, Hatch B


Introduction to the simplest kind of neural network: feedforward. We'll start with a linear classifier called logistic regression and see why it can't solve certain problems, then we'll see how a simple (*almost* deep) neural network can solve those problems. The desired outcome of this presentation is for participants to understand, at least in part, how neural networks "learn" and what makes them so effective for certain tasks. We'll be using Python to work through some of the concepts.

Presenter Bio

Assistant Professor at Boise State University in the Department of Computer Science. PhD in Computational Linguistics from Bielefeld University, Germany. Researching spoken dialogue systems and language acquisition.