Bug#556167: ITP: scilab-ann -- Scilab toolbox for artificial neural networks
Package: wnpp
Severity: wishlist
Owner: Sylvestre Ledru <sylvestre.ledru@inria.fr>
* Package name : scilab-ann
Version : 0.4.2.3
Upstream Author : Ryurick M. Hristev <r.hristev@phys.canterbury.ac.nz>
* URL : http://atoms.scilab.org/toolboxes/ANN_Toolbox/
* License : GPL 2
Programming Lang: Scilab
Description : Scilab toolbox for artificial neural networks
Current features
- Only layered feedforward networks are supported *directly* at the moment
(for others use the "hooks" provided)
- Unlimited number of layers
- Unlimited number of neurons per each layer separately
- User defined activation function (defaults to logistic)
- User defined error function (defaults to SSE)
- Algorithms implemented so far:
* standard (vanilla) with or without bias, on-line or batch
* momentum with or without bias, on-line or batch
* SuperSAB with or without bias, on-line or batch
* Conjugate gradients
* Jacobian computation
* Computation of result of multiplication between "vector" and Hessian
- Some helper functions provided
Reply to: