Optimizing method for Neural Network based on Genetic Random Weight Change Learning Algorithm

TL;DR

This paper introduces a novel hybrid algorithm called Genetic Random Weight Change (GRWC) that combines RWC and GA to optimize neural networks more effectively, demonstrated on the MNIST dataset.

Contribution

The paper proposes a new hybrid optimization method for neural networks that reduces complexity and improves learning by combining RWC and GA techniques.

Findings

GRWC effectively explores complex optimization spaces.

The method reduces neural network complexity by removing weak weights.

Demonstrated improved performance on MNIST dataset.

Abstract

Random weight change (RWC) algorithm is extremely component and robust for the hardware implementation of neural networks. RWC and Genetic algorithm (GA) are well known methodologies used for optimizing and learning the neural network (NN). Individually, each of these two algorithms has its strength and weakness along with separate objectives. However, recently, researchers combine these two algorithms for better learning and optimization of NN. In this paper, we proposed a methodology by combining the RWC and GA, namely Genetic Random Weight Change (GRWC), as well as demonstrate a seminal way to reduce the complexity of the neural network by removing weak weights of GRWC. In contrast to RWC and GA, GRWC contains an effective optimization procedure which is worthy at exploring a large and complex space in intellectual strategies influenced by the GA/RWC synergy. The learning behavior of the proposed algorithm was tested on MNIST dataset and it was able to prove its performance.