Description: I write the GramSchmidt neural network algorithm, compared with the traditional neural network algorithm, this algorithm can automatically generate neurons, save time, speed!
I also added a automatic classification method and suitable for all kinds of function transformation, the zip contains two files, one is GramSchmidt orthogonal decomposition, as is the function, the main function is orth_GramSchmidt, in the same directory, you can run, approximation and classification of the benchmark problems provide solution - I prepared GramSchmidt neural network algorithm, and the traditional neural network algorithm, the algorithm can automatically generate neurons, saving time, fast! I also added a method of automatically generated classification and conversion, for a variety of functions provides the zip includes two documents, one is GramSchmidt orthogonal decomposition is a sub - function, the main function is orth_GramSchmidt, on the same directory, you can run can benchmark approximation and classification problems to dojo.provide solutions
To Search:
File list (Check if you may need any files):
Download