Random Neural Networks
CMSA Room G10 CMSA, 20 Garden Street, Cambridge, MA, United StatesProbability Seminar Speaker: Boris Hanin (Princeton) Title: Random Neural Networks Abstract: Fully connected neural networks are described two by structural parameters: a depth L and a width N. In this talk, I will present results and open questions about the asymptotic analysis of such networks with random weights and biases in the regime where N (and potentially […]