Simultaneous Optimization of Neural Network Weights and Active Nodes using Metaheuristics
This work addresses the issue of suboptimal performance due to homogeneous activation functions in neural networks, offering an incremental improvement for researchers and practitioners in machine learning optimization.
The paper tackled the problem of neural network optimization by introducing customizable transfer functions with tunable parameters to create heterogeneity, and found that using Artificial Bee Colony with adaptive transfer functions achieved the best classification accuracy on benchmark datasets compared to other metaheuristics like particle swarm optimization and differential evolution.
Optimization of neural network (NN) significantly influenced by the transfer function used in its active nodes. It has been observed that the homogeneity in the activation nodes does not provide the best solution. Therefore, the customizable transfer functions whose underlying parameters are subjected to optimization were used to provide heterogeneity to NN. For the experimental purpose, a meta-heuristic framework using a combined genotype representation of connection weights and transfer function parameter was used. The performance of adaptive Logistic, Tangent-hyperbolic, Gaussian and Beta functions were analyzed. In present research work, concise comparisons between different transfer function and between the NN optimization algorithms are presented. The comprehensive analysis of the results obtained over the benchmark dataset suggests that the Artificial Bee Colony with adaptive transfer function provides the best results in terms of classification accuracy over the particle swarm optimization and differential evolution.