arXiv Machine Learning By Emily Dent, Jared Tanner

How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs

Read the original on arXiv Machine Learning →

arXiv:2602. 05779v2 Announce Type: replace Abstract: The Edge-of-Chaos (EoC) theory developed for the random initialization of deep networks allows more efficient training by both preserving information in the initial outputs of the network and minimising exploding or vanishing gradients through characterisation of the intermediate layers as Gaussian processes.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.