a set of C++ library classes
for neural networks development



File for storing Multi-Layer Perceptron

File for storing weights and parameters of a MLP.
The file stores the neural net, i.e. its weights and parameters. The file stores the following information: If you want reload the stored MLP, don't edit this file. The suffix of this file is .net.

Example:
The following example stores a Two-Layer MLP with 4 hidden units, three-dimensional input and six outputs:

Version:  1
p6.net
Number_layers:    2
Dim_output:       6    Act.function: 1
Dim_hidden1:      4    Act.function: 1
Dim_input:        3

Weight matrix output layer :
+2.15923085 -2.45975410 -0.88109598 +0.93735627 
-0.41550944 +2.08865904 -3.86896036 -0.03048399 
-2.78962989 -1.53053199 -1.31088928 +2.07159140 
-0.68062739 -3.37259294 +2.79630147 -1.51406900 
+2.86396859 +0.58541817 -0.78466628 -2.16585108 
-2.52104348 +2.16025013 +0.55498627 -2.79712976 
Bias vector:
-2.07666933 -0.79373344 +0.16611944 -0.94844541 -1.72233196 -0.75307911 

Weight matrix hidden layer :
+0.95333027 -2.87205005 -1.18164714 
+0.33952172 -0.54502282 +3.39657025 
+2.10828810 +0.55708249 -0.89277724 
-2.94175113 -0.41389183 -0.96580138 
Bias vector:
-0.23028497 +0.16500146 +0.38169703 -0.55625551 

END

Alphabetic index Hierarchy of classes


Last Updated February 2001
For comments and suggestions mail to Giorgio Valentini