Machine learning | MATLAB implements BP neural network model answering (fitness function)
Table of contents
basic introduction
Machine learning | MATLAB implements BP neural network model answering (fitness function) and Bayesian optimization
Answer one
When using genetic algorithm to optimize BP neural network, the setting of fitness function is very important. The role of the fitness function is to evaluate the pros and cons of each individual (that is, the BP neural network), thereby guiding the search process of the evolutionary algorithm.
The fitness function should reflect the performance of the BP neural network. There are two common fitness functions:
- mean square error fitness function
- The fitness function can be set to the mean square error (MSE) of the BP neural network on the training set or the mean square error on the cross-validation set, namely: