Optimizing Neural Network Weights using Nature-Inspired Algorithms
This work addresses improving neural network training efficiency for medical diagnosis tasks, but it is incremental as it builds on existing optimization methods.
The study tackled optimizing deep feedforward neural network weights using nature-inspired algorithms like PSO, MTO, and MTOCL, showing that MTOCL performed best across three breast cancer datasets, with superior results on challenging prognostic data.
This study aims to optimize Deep Feedforward Neural Networks (DFNNs) training using nature-inspired optimization algorithms, such as PSO, MTO, and its variant called MTOCL. We show how these algorithms efficiently update the weights of DFNNs when learning from data. We evaluate the performance of DFNN fused with optimization algorithms using three Wisconsin breast cancer datasets, Original, Diagnostic, and Prognosis, under different experimental scenarios. The empirical analysis demonstrates that MTOCL is the most performing in most scenarios across the three datasets. Also, MTOCL is comparable to past weight optimization algorithms for the original dataset, and superior for the other datasets, especially for the challenging Prognostic dataset.