5.6. Genetic Algorithm for Multi-Layer Networks
Another school of thought to train neural networks is to use an evolutionary search such as genetic algorithms [114, 243], evolutionary programming [100, 101], and evolution strategies [296, 325,338]. This section presents a hybrid algorithm that combines the standard RBF learning and genetic algorithms to find the parameters of RBF networks.
Unlike a local search, an evolutionary search maintains a population of potential solutions rather than a single solution. Therefore, the risk of getting stuck in local optima is smaller. Each candidate solution represents one neural network in which the weights can be encoded as a string of binary [71, 381, 383] or floating point numbers [119, 240, 283,
Get Biometric Authentication: A Machine Learning Approach now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
