Netlearn

This is a SNNS kernel backpropagation test program. It is a demo for using the SNNS kernel interface to train networks.

Synopsis: netlearn

example:

 
		  unix> netlearn

produces

		 SNNS 3D-Kernel V 3.3

		 ---Network learning---

		 Filename of the network file: letters_untrained.net

		 Loading the network...

		 Network name: letters

		 No. of units: 		 71

		 No. of input units: 		 35

		 No. of output units: 		 26

		 No. of sites: 		 0

		 No. of links: 		 610

		 Learning function: 		 Std_Backpropagation

		 Update function: 		 Topological_Order

		 Filename of the patternfile: letters.pat

		 loading the patterns...

		 Number of pattern: 		 26

		 The learning function  Std_Backpropagation needs 2 input parameters:

		 Parameter [1]: 		 0.6

		 Parameter [2]: 		 0.6

		 Choose number of cycles: 250

		 Shuffle patterns (y/n) 		 n

		 Shuffling of patterns disabled

		 learning...