AUXIL\
ffn__define.pro
Class description for FFN
Subclasses: FFNBP FFNCG FFNKAL
Fields
Fields in FFN
- N ptr_new()
- KK 0L
- NN 0L
- NP 0L
- WH ptr_new()
- LL 0L
- WO ptr_new()
- LS ptr_new()
- GS ptr_new()
Routines
result = FFN::Init(Gs, Ls, L)Object class for implementation of a two-layer, feed-forward neural network classifier.
result = FFN::forwardPass(G)result = FFN::classify(Gs, Probs)result = FFN::vForwardPass(Gs, N)result = FFN::cost(key)result = FFN::GetWeights()FFN::PutWeights, wFFN::CleanupFFN__Define
Routine details
top FFN::Init
Object class for implementation of a two-layer, feed-forward neural network classifier. This is a generic class with no training method
Parameters
- Gs in required
array of observation column vectors
- Ls in required
array of class label column vectors of form (0,0,1,0,0,...0)^T
- L in required
number of hidden neurons
Author information
- Author:
Mort Canty (2009)
top FFN::GetWeights
result = FFN::GetWeights()
top FFN::Cleanup
FFN::Cleanup
top FFN__Define
FFN__Define
File attributes
| Modification date: | Wed Apr 15 11:49:30 2009 |
| Lines: | 142 |
| Docformat: | rst rst |