AUXIL\
ffncg__define.pro
Class description for FFNCG
Inheritance
Properties
Properties in FFNCG
- epochs init
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()
Fields in FFNCG
- EPOCHS 0L
- LTS ptr_new()
- NTP 0L
- VALID_COST_ARRAY ptr_new()
- GTS ptr_new()
- COST_ARRAY ptr_new()
Routines
result = FFNCG::Init(Gs, Ls, L, epochs=epochs)Object class for implementation of a two-layer, feed-forward neural network classifier.
FFNCG::Cleanupresult = FFNCG::Gradient()result = FFNCG::Rop(V)result = FFNCG::Hessian()result = FFNCG::Eigenvalues()FFNCG::Train, key=keyFFNCG__Define
Routine details
top FFNCG::Init
result = FFNCG::Init(Gs, Ls, L, epochs=epochs)
Object class for implementation of a two-layer, feed-forward neural network classifier. Implements scaled conjugate gradient training:
Bishop, C. M. (1995). Neural Networks for
Pattern Recognition. Oxford ;University Press.
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
Keywords
- epochs
Examples
ffn = Obj_New("FFNCG",Gs,Ls,L)
Author information
- Author:
Mort Canty (2009)
Other attributes
- Uses:
COYOTE
top FFNCG::Cleanup
FFNCG::Cleanup
top FFNCG::Gradient
result = FFNCG::Gradient()
top FFNCG::Hessian
result = FFNCG::Hessian()
top FFNCG::Eigenvalues
result = FFNCG::Eigenvalues()
top FFNCG__Define
FFNCG__Define
File attributes
| Modification date: | Mon Aug 18 13:32:17 2014 |
| Lines: | 211 |
| Docformat: | rst rst |