avb@tnoibbc.UUCP (Andre van Brussel) (04/16/91)
Hi, I am looking for a implementation solving the XOR problem using a Multi-Layer Perceptron. The problem is that I can't find a good learning rule for the so called hidden layer in the Perceptron Network. An elementary problem like solving XOR in a 3 layer Perceptron can help me to find out the learning principles of a MLP. Anyone who seems to have the algorithm for this, or a C/Pascal source please email.... I do have a Back Error Prop. approach for solving the XOR, but this does not include a source. ~ Institute TNO for Building Materials and Structures (TNO-Bouw) Andre van Brussel -_-_-_-_-_-_-_-_-_-_-_-_-_-_ PO BOX 49 tel: +31 15 842019 UUCP : ..!hp4nl!tnoibbc!avb 2600 AA Delft fax: +31 15 843990 USENET: avb@tnoibbc The Netherlands -- Institute TNO for Building Materials and Structures (TNO-Bouw) Andre van Brussel -_-_-_-_-_-_-_-_-_-_-_-_-_-_ PO BOX 49 tel: +31 15 842019 UUCP : ..!hp4nl!tnoibbc!avb 2600 AA Delft fax: +31 15 843990 USENET: avb@tnoibbc The Netherlands