Papers › Mean Field Theory of Activation Functions in Deep Neural Networks

Mean Field Theory of Activation Functions in Deep Neural Networks

22 May 2018arXiv:1805.08786archive 2025-07-28

Mirco Milletarí, Thiparat Chotibut, Paolo E. Trevisanutto

We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach. We infer that FFN can be understood as performing three basic steps: encoding, representation validation and propagation. From the meanfield solution of the model, we obtain a set of natural activations -- such as Sigmoid, tanh and ReLu -- together with the state-of-the-art, Swish; this represents the expected information propagating through the network and tends to ReLu in the limit of zero noise.We study the spectrum of the Hessian on an associated classification task, showing that Swish allows for more consistent performances over a wider range of network architectures.

PaperPDFCode

Code

WessZumino/meanfield-theory-of-activation-functions officialmentioned in papermentioned on GitHubtf report
WessZumino/expectation_propagation mentioned on GitHubtfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ReLUSigmoid Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections