To improve the algorithm from the method for determining the hidden layer neurons, the initial range of weights and thresholds, the error function and adaptive learning rate back-propagation algorithm to improve the network convergence speed of the purpose of ; the introduction of the genetic algori

The algorithm from hidden layer neuron a method for determining, weight and threshold of the Initial Value field, error functions, and the adaptive learning rate of error in such as anti-pass algorithms to improve and to increase the speed of network convergence of purpose, and once again introduced

This algorithm from concealment level neuron integer definite aspects and so on method, weight and valve value starting value territory, error function and auto-adapted study speed makes the improvement to the erroneous counter-biography algorithm, achieved enhances the network the convergence rate

The algorithm from the method of determining the number of hidden layer neurons, weights and thresholds of the initial domain, error function and adaptive learning rate, improvements to the error back propagation algorithm, for increasing the speed of convergence of the network purpose; at the same

正在翻譯，請等待...