On the quasi-Newton training method for feed-forward neural networks
Nikolai Stanevski, Dimiter Tsvetkov · 2004
The quasi-Newton training method is the most effective method for feed-forward neural networks with respect to the training precision. This method is well-known and popularly described in the neural networks literature. Nevertheless its implementation contains some difficulties because of the specific shape of the cost function and the large amount of variables. Here we give in sufficient details an example of a program implementation of the quasi-Newton method. This implementation (as a Borland Delphi application) seems to work well with various examples.