A Genetic Algorithm based Kernel-size Selection Approach for a Multi-column Convolutional Neural Network

TL;DR

This paper proposes a genetic algorithm-based method to efficiently select optimal kernel sizes for multi-column convolutional neural networks, reducing the experimental effort needed for hyper-parameter tuning.

Contribution

It introduces a novel genetic algorithm approach specifically for kernel size selection in CNN architectures, streamlining hyper-parameter optimization.

Findings

Effective kernel size selection on Bangla character datasets

Reduces manual experimentation in CNN hyper-parameter tuning

Demonstrates improved model performance with optimized kernels

Abstract

Deep neural network-based architectures give promising results in various domains including pattern recognition. Finding the optimal combination of the hyper-parameters of such a large-sized architecture is tedious and requires a large number of laboratory experiments. But, identifying the optimal combination of a hyper-parameter or appropriate kernel size for a given architecture of deep learning is always a challenging and tedious task. Here, we introduced a genetic algorithm-based technique to reduce the efforts of finding the optimal combination of a hyper-parameter (kernel size) of a convolutional neural network-based architecture. The method is evaluated on three popular datasets of different handwritten Bangla characters and digits. The implementation of the proposed methodology can be found in the following link: https://github.com/DeepQn/GA-Based-Kernel-Size.