Description:

Title: Error-free Training for Artificial Neural Networks

Zoom Link: https://illinois.zoom.us/j/82616248519pwd=CAR0v0aaIpTnIVwxJDa59wFvusobot.1

Abstract:

If we define intelligence as not making the same mistake twice, then a system achieves this artificial intelligence if and only if it can learn from its mistakes every time. For a feedforward neural network under supervised training, this means that it can be trained error-free for every data set. This problem is known as the discreet classification problem in mathematics. Its solution was obtained more than thirty years ago by what is now known as the Universal Approximation Theorem. In this talk, I will present a numerical algorithm to fulfill the UAT. I will illustrate the algorithm by both abstract and practical classification problems.

Bio:

Bo Deng is a Professor of Mathematics at the University of Nebraska, Lincoln

The Midwest Mathematical Biology Seminar will be a series of virtual talks on mathematical biology featuring speakers from the Midwest region and beyond. All areas of mathematical biology will be represented in the seminar series, and a goal for this seminar is to build connections and foster research collaborations.

More information - https://sites.google.com/view/midwest-mathbio-seminar/home