Event Date
Mathematics-Statistics Joint Colloquium 2025
Speaker: Sourav Chatterjee (Professor of Statistics and Mathematics, Stanford University)
Title: "Neural networks can learn any low complexity pattern"
Abstract: I will present recent work showing that feedforward neural networks can, in principle, learn patterns that can be expressed as a short program. An example is as follows. Let N be a large number, and suppose our data consists of a sample of X’s and Y’s, where each X is a randomly chosen number between 1 and N, and the corresponding Y is 1 if X is a prime and 0 if not. The sample size n is negligible compared to N. If we fit a neural network to this data which is “sparsest” in a suitable sense, it turns out that the network will be able to accurately predict if a newly chosen X is a prime or not. This is because the property of being prime can be tested by a short program. This is based on joint work with Tim Sudijono. The talk will be accessible to those with no background in neural networks.
Faculty web-page (links to Stanford Univ.): https://statistics.stanford.edu/people/sourav-chatterjee