Bayesian Inference with Deep Weakly Nonlinear Networks

B Hanin, A Zlokapa - arXiv preprint arXiv:2405.16630, 2024 - arxiv.org
We show at a physics level of rigor that Bayesian inference with a fully connected neural
network and a shaped nonlinearity of the form $\phi (t)= t+\psi t^ 3/L $ is (perturbatively) …