On randomization of neural networks as a form of post-learning strategy

TL;DR

This paper proposes a novel post-learning randomization strategy inspired by quantum effects to improve neural network training outcomes, addressing local minima issues with minimal additional computation.

Contribution

It introduces a new randomization technique based on quantum analogy as a post-learning method to enhance neural network performance.

Findings

Improves neural network training results

Addresses local minimum problem effectively

Requires minimal extra computational cost

Abstract

Today artificial neural networks are applied in various fields - engineering, data analysis, robotics. While they represent a successful tool for a variety of relevant applications, mathematically speaking they are still far from being conclusive. In particular, they suffer from being unable to find the best configuration possible during the training process (local minimum problem). In this paper, we focus on this issue and suggest a simple, but effective, post-learning strategy to allow the search for improved set of weights at a relatively small extra computational cost. Therefore, we introduce a novel technique based on analogy with quantum effects occurring in nature as a way to improve (and sometimes overcome) this problem. Several numerical experiments are presented to validate the approach.