Training feedforward neural networks with Bayesian hyper-heuristics

Arné Schreuder, Anna S. Bosman, Andries P. Engelbrecht, Christopher W. Cleghorn

Abstract: Highlights•A novel Bayesian hyper-heuristic (BHH) is developed and shown to efficiently train feedforward neural networks (FFNNs).•The BHH shows statistically significant performance on multiple problems, comparable to the best heuristics.•The BHH produces good results with a diverse set of low-level heuristics across multiple problems.•The BHH automates heuristic selection for FFNN training, reducing manual trial and error.•The BHH can utilise a priori1 knowledge for low-level heuristics selection on specific problems.