Investigate the use of back-propagation learning employing a sigmoidal nonlinearity to achieve one-to-one mappings, as described here:
For each mapping, do the following:
(a) Set up two sets of data, one for network training, and the other for testing.
(b) Use the training data set to compute the synaptic weights of the network, assumed to have a single hidden layer.
(c) Evaluate the computation accuracy of the network by using the test data
Use a single hidden layer, but with a variable number of hidden neurons. Investigate how the network performance is affected by varying the size of the hidden layer.