A Genetic Algorithm based Kernel-size Selection Approach for a Multi-column Convolutional Neural Network
This work addresses a tedious hyperparameter optimization problem for researchers and practitioners in pattern recognition, but it is incremental as it applies an existing method (genetic algorithm) to a specific bottleneck.
The paper tackles the challenge of selecting optimal kernel sizes in convolutional neural networks by introducing a genetic algorithm-based approach, achieving competitive results on three handwritten Bangla character and digit datasets.
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.