bpn.edt

Backpropagation Network Time-Series Forecasting 源码, 经典的BPN人工神经网络例子源码

NMSE is 0.879 on Training Set and 0.834 on Test Set - saving Weights ...
NMSE is 0.818 on Training Set and 0.783 on Test Set - saving Weights ...
NMSE is 0.749 on Training Set and 0.693 on Test Set - saving Weights ...
NMSE is 0.691 on Training Set and 0.614 on Test Set - saving Weights ...
NMSE is 0.622 on Training Set and 0.555 on Test Set - saving Weights ...
NMSE is 0.569 on Training Set and 0.491 on Test Set - saving Weights ...
NMSE is 0.533 on Training Set and 0.467 on Test Set - saving Weights ...
NMSE is 0.490 on Training Set and 0.416 on Test Set - saving Weights ...
NMSE is 0.470 on Training Set and 0.401 on Test Set - saving Weights ...
NMSE is 0.441 on Training Set and 0.361 on Test Set - saving Weights ...
.
.
.
NMSE is 0.142 on Training Set and 0.143 on Test Set
NMSE is 0.142 on Training Set and 0.146 on Test Set
NMSE is 0.141 on Training Set and 0.143 on Test Set
NMSE is 0.146 on Training Set and 0.141 on Test Set
NMSE is 0.144 on Training Set and 0.141 on Test Set
NMSE is 0.140 on Training Set and 0.142 on Test Set
NMSE is 0.144 on Training Set and 0.148 on Test Set
NMSE is 0.140 on Training Set and 0.139 on Test Set - saving Weights ...
NMSE is 0.140 on Training Set and 0.140 on Test Set
NMSE is 0.141 on Training Set and 0.138 on Test Set - saving Weights ...
.
.
.
NMSE is 0.104 on Training Set and 0.154 on Test Set
NMSE is 0.102 on Training Set and 0.160 on Test Set
NMSE is 0.102 on Training Set and 0.160 on Test Set
NMSE is 0.100 on Training Set and 0.157 on Test Set
NMSE is 0.105 on Training Set and 0.153 on Test Set
NMSE is 0.100 on Training Set and 0.155 on Test Set
NMSE is 0.101 on Training Set and 0.154 on Test Set
NMSE is 0.100 on Training Set and 0.158 on Test Set
NMSE is 0.107 on Training Set and 0.170 on Test Set - stopping Training
                                                      and restoring Weights ...
NMSE is 0.141 on Training Set and 0.138 on Test Set


Year    Sunspots    Open-Loop Prediction    Closed-Loop Prediction

1960       0.572                   0.532                     0.532
1961       0.327                   0.334                     0.301
1962       0.258                   0.158                     0.146
1963       0.217                   0.156                     0.098
1964       0.143                   0.236                     0.149
1965       0.164                   0.230                     0.273
1966       0.298                   0.263                     0.405
1967       0.495                   0.454                     0.552
1968       0.545                   0.615                     0.627
1969       0.544                   0.550                     0.589
1970       0.540                   0.474                     0.464
1971       0.380                   0.455                     0.305
1972       0.390                   0.270                     0.191
1973       0.260                   0.275                     0.139
1974       0.245                   0.211                     0.158
1975       0.165                   0.181                     0.170
1976       0.153                   0.128                     0.175
1977       0.215                   0.151                     0.193
1978       0.489                   0.316                     0.274
1979       0.754                   0.622                     0.373