Date/Time
Date(s) - 01/12/2023
11:00 am - 12:00 pm

Location: Zoom Meeting

Speaker: Teun van Nuland (University of New South Wales, Sydney)

Title: Universal Approximation on all of R^n

Abstract:
The universal approximation theorem is generalised to uniform convergence on the (noncompact) input space Rn. All continuous functions that vanish at infinity can be uniformly approximated by neural networks with one hidden layer, for all continuous activation functions phi (is not) = 0 with asymptotically linear behaviour at ±phi. When phi is moreover bounded, we exactly determine which functions can be uniformly approximated by neural networks, with the following unexpected results.

Link:
https://mcmaster.zoom.us/j/91260076066

Meeting ID: 912 6007 6066
Passcode: 065564