Neural Network Training

Abstract

The program trains several neural networks (that vary in their number of hidden layer neurons) and enables users to pick the best. The program trains the networks using input and target data contained in files named Inputs1.txt and Targets1.txt respectively. The program randomly splits the supplied data into 3 portions: 70% for training, 15% for validation, and 15% for testing. The user has the option to change this proportioning in lines 68 to 70. The user also has the option to use his/her own test data: these should be saved in same format as Inputs2.txt and Targets2.txt When the program runs, it trains 100 different networks: the networks differ in their number of hidden layer neurons. The networks generated are saved in in a folder named networks, within the same folder where this program is run. The network saved as net1 has 1 hidden layer neuron, net2 has 2, net3 has 3, net4 has 4.