Optimizing multilayer Bayesian neural networks for evaluation of fission yields

TL;DR

This paper enhances multilayer Bayesian neural networks to improve the evaluation of nuclear fission yields by optimizing data, architecture, and activation functions, ensuring physically meaningful results.

Contribution

It introduces optimized multilayer Bayesian neural networks with specific adjustments for more accurate fission yield evaluations.

Findings

Double hidden layer networks perform best.

Penalizing negative net function values prevents non-physical results.

Optimized network configurations improve evaluation accuracy.

Abstract

The Bayesian machine learning is a promising tool for the evaluation of nuclear fission data but its potential capability has not been fully realized. We attempt to optimize the performances of the multilayer Bayesian neural networks for evaluations of fission yields. The influences of adjustments of learning data, activation functions, network structures have been studied. In particular, negative values of net functions have been penalized to avoid non-physical inferences of fission yields. Presently the network with double hidden layers has optimal performances compared to the single-layer or deeper networks. These studies are essential for further developments of precise evaluation methods.