Optimizing the Neural Network Parameters

There may be times when you are not sure how many hidden processing elements your neural network should have or which inputs are providing useful information. NeuroSolutions can adjust parameters and select inputs for you automatically. The technique it uses is genetic optimization, which uses a form of artificial intelligence known as a genetic algorithm to search for the best combination of parameters and inputs. It will train your neural network many times while adjusting the parameters and excluding inputs based on the laws of evolution (survival of the fittest). Once the genetic training is complete, you end up with the settings that produced the lowest error. The network attributes that are most commonly optimized include:

Learning Rates	Weights
Number of Memory Taps	Data Flow Through Network
Choice of Inputs	Number of Hidden Processing Elements

Back | Tour Topics | Next