Package: scilab-ann Binary: scilab-ann Version: 0.4.2.4-1 Priority: optional Section: math Maintainer: Debian Science Team Build-Depends: debhelper (>= 7), cdbs, scilab (>= 5.1.1), scilab-doc (>= 5.3.0) Architecture: all Standards-Version: 3.9.1 Format: 3.0 (quilt) Directory: pool/main/s/scilab-ann Files: 9df5d6d6f5cbf264b264f4583b09f781 1379 scilab-ann_0.4.2.4-1.dsc 8dd07c44b0a172de0e7e71eefb51be5c 30024 scilab-ann_0.4.2.4.orig.tar.gz af00887781b8b9069a4d7545367997f0 10454 scilab-ann_0.4.2.4-1.debian.tar.gz Uploaders: Sylvestre Ledru Homepage: http://atoms.scilab.org/toolboxes/ANN_Toolbox/ Vcs-Browser: http://svn.debian.org/viewsvn/debian-science/packages/scilab-toolboxes/ann/trunk Vcs-Svn: svn://svn.debian.org/svn/debian-science/packages/scilab-toolboxes/ann/trunk Checksums-Sha1: 6910beae4b392f4da93c2ef6ebf7597a61cbcb1b 30024 scilab-ann_0.4.2.4.orig.tar.gz af793b5c0090227faa7d072d41a08c26a350f6a3 10454 scilab-ann_0.4.2.4-1.debian.tar.gz Checksums-Sha256: b8a0978c25ad5cd805c32e5c731fb323c24e2f52a9cb1b7f343387ec90667482 30024 scilab-ann_0.4.2.4.orig.tar.gz fa360e6c76dde784d2c72cec63a3e564b85524d772fb8d1ca1a65897dd8872e3 10454 scilab-ann_0.4.2.4-1.debian.tar.gz Package: scilab-ann Priority: optional Section: math Installed-Size: 704 Maintainer: Debian Science Team Architecture: all Version: 0.4.2.4-1 Depends: scilab (>= 5.1.1) Filename: pool/main/s/scilab-ann/scilab-ann_0.4.2.4-1_all.deb Size: 130958 MD5sum: b3c1315fda84e0d587640623fe105967 SHA1: 01e20a9413dae92f44c4507c3b161dc4b657d320 SHA256: 6bf751d7b9c1bb8277d05a5e128a22dcbbf8bf54e76c2f3529e971258b093b51 Description: Scilab module for artificial neural networks This module implements artificial neural networks capabilities into the Scilab language. Current features are: * 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 Homepage: http://atoms.scilab.org/toolboxes/ANN_Toolbox/ Tag: devel::library, role::devel-lib, role::shared-lib