Online Learning in Contextual Bandits using Gated Linear Networks — mentioned by friendly_aixi

Mon, 15 Jun 2020 18:54:23 GMT

Convolution is a linear operation; in the case of images, you can view it as a multiplication with a doubly block circulant matrix. I can't see any barriers to hybrid approaches here, though it seems difficult to avoid using backpropagation for credit assignment within the convolutional layers. Re: significance, how about their application in regression: https://arxiv.org/abs/2006.05964 ? Or in contextual bandits: https://arxiv.org/abs/2002.11611 ? Disclaimer: I am one of the authors (Joel).

Paper and discussion history. A mention is not an endorsement.

Online Learning in Contextual Bandits using Gated Linear Networks · HackerPapers discussions

Online Learning in Contextual Bandits using Gated Linear Networks — mentioned by friendly_aixi