Monday May 1, 2017 12:00 PM

Representation power of neural networks.

Speaker: Matus Telgarsky, Computer Science, University of Illinois, Urbana-Champaign
Location: Annenberg 213

This talk will present a series of mathematical vignettes on the representation power of neural networks.  Amongst old results, the classical universal approximation theorem will be presented, along with Kolmogorov's superposition theorem.  Recent results will include depth hierarchies (for any choice of depth, there exists functions which can only be approximated by slightly less deep networks when they have exponential size), connections to polynomials (namely, rational functions and neural networks well-approximate each other), and the power of recurrent networks.  Open problems will be sprinkled throughout.

Series Rigorous Systems Research Group (RSRG) Seminar Series

Contact: Sheila Shull at 626.395.4560