patmat.chk

著名的神经网络工具箱

=============================================================================
	This file contains data to test the learning functions
=============================================================================

Network-Files:	patmat_untrained.net
==============	

Pattern-Files:	patmat.pat
==============	

Description:	- load network patmat_untrained.net	
============	- load patterns patmat.pat	
		- do NOT press init button
		- set cycles to 50
		- set shuffle off 
		- for each test set:
			- set learing function given in test set.
			- set learning parameters given in test set.
			- set update function given in test set.
			- set update parameters given in test set.
			- press the all button
			- compare the results with the given results 
			- reload network patmat_untrained.net	

Test set 1)
===========

learning function  : Std_Backpropagation          0.2   0.0   0.0   0.0   0.0
update function    : Topological_Order		  0.0   0.0   0.0   0.0   0.0

  epoch:         SSE            MSE            SSE/o-units

     50:      57.43739        9.57290           1.64107
     45:      28.33091        4.72182           0.80945
     40:      23.36288        3.89381           0.66751
     35:      20.37907        3.39651           0.58226
     30:      17.96514        2.99419           0.51329
     25:      15.86678        2.64446           0.45334
     20:      14.01956        2.33659           0.40056
     15:      12.44866        2.07478           0.35568
     10:      11.16080        1.86013           0.31888
      5:      10.10911        1.68485           0.28883
      1:       9.40102        1.56684           0.26860


Test set 2)
===========

learning function  : Backpropagation with Momentum 0.8   0.6   0.1   0.0   0.0
update function    : Topological_Order		   0.0   0.0   0.0   0.0   0.0

  epoch:         SSE            MSE            SSE/o-units

     50:      47.82394        7.97066           1.36640
     45:      11.88784        1.98131           0.33965
     40:       3.60736        0.60123           0.10307
     35:       1.60474        0.26746           0.04585
     30:       0.78967        0.13161           0.02256
     25:       0.54716        0.09119           0.01563
     20:       0.39293        0.06549           0.01123
     15:       0.28987        0.04831           0.00828
     10:       0.23189        0.03865           0.00663
      5:       0.19119        0.03186           0.00546
      1:       0.16657        0.02776           0.00476

Test set 3)
===========

learning function  : Quickprop                     0.2   1.75  0.0001 0.0   0.0
update function    : Topological_Order		   0.0   0.0   0.0    0.0   0.0

  epoch:         SSE            MSE            SSE/o-units

     50:      62.20805       10.36801           1.77737
     45:      13.83142        2.30524           0.39518
     40:       3.36853        0.56142           0.09624
     35:       1.29989        0.21665           0.03714
     30:       4.97972        0.82995           0.14228
     25:       0.23330        0.03888           0.00667
     20:       0.07586        0.01264           0.00217
     15:       0.01147        0.00191           0.00033
     10:       0.00332        0.00055           0.00009
      5:       0.00180        0.00030           0.00005
      1:       0.00165        0.00028           0.00005


Test set 4)
===========

learning function  : Rprop                         0.2   0.0   0.0   0.0   0.0
update function    : Topological_Order		   0.0   0.0   0.0   0.0   0.0

  epoch:         SSE            MSE            SSE/o-units

     50:      57.43744        9.57291           1.64107
     45:      28.33092        4.72182           0.80945
     40:      23.36290        3.89382           0.66751
     35:      20.37909        3.39651           0.58226
     30:      17.96515        2.99419           0.51329
     25:      15.86679        2.64447           0.45334
     20:      14.01958        2.33660           0.40056
     15:      12.44868        2.07478           0.35568
     10:      11.16081        1.86014           0.31888
      5:      10.10913        1.68485           0.28883
      1:       9.40103        1.56684           0.26860