ffnet version 0.6 is now released. Source packages, Gentoo ebuilds and Windows binaries are now available for download at:
http://ffnet.sourceforge.net The last public release was 0.5. If you are unfamiliar with this package, see the end of this message for a description. NEW FEATURES - trained network can be now exported to fortran source code and compiled - added new architecture generator (imlgraph) - added rprop training algorithm - added draft network plotting facility (based on networkx and matplotlib) CHANGES & BUG FIXES - fixed bug preventing ffnet form working with networkx-0.33 - training data can be now numpy arrays - ffnet became a package now, but API should be compatibile with previous version DOCUMENTATION - docstrings of all objects have been improved - docs (automatically generated with epydoc) are avilable online and have been included to source distribution What is ffnet? -------------- ffnet is a fast and easy-to-use feed-forward neural network training solution for python. Unique features --------------- 1. Any network connectivity without cycles is allowed. 2. Training can be performed with use of several optimization schemes including: standard backpropagation with momentum, rprop, conjugate gradient, bfgs, tnc, genetic alorithm based optimization. 3. There is access to exact partial derivatives of network outputs vs. its inputs. 4. Automatic normalization of data. Basic assumptions and limitations: ---------------------------------- 1. Network has feed-forward architecture. 2. Input units have identity activation function, all other units have sigmoid activation function. 3. Provided data are automatically normalized, both input and output, with a linear mapping to the range (0.15, 0.85). Each input and output is treated separately (i.e. linear map is unique for each input and output). 4. Function minimized during training is a sum of squared errors of each output for each training pattern. Performance ----------- Excellent computational performance is achieved implementing core functions in fortran 77 and wrapping them with f2py. ffnet outstands in performance pure python training packages and is competitive to 'compiled language' software. Moreover, a trained network can be exported to fortran sources, compiled and called from many programming languages. Usage ----- Basic usage of the package is outlined below: from ffnet import ffnet, mlgraph, savenet, loadnet, exportnet conec = mlgraph( (2,2,1) ) net = ffnet(conec) input = [ [0.,0.], [0.,1.], [1.,0.], [1.,1.] ] target = [ [1.], [0.], [0.], [1.] ] net.train_tnc(input, target, maxfun = 1000) net.test(input, target, iprint = 2) savenet(net, "xor.net") exportnet(net, "xor.f") net = loadnet("xor.net") answer = net( [ 0., 0. ] ) partial_derivatives = net.derivative( [ 0., 0. ] ) Usage examples with full description can be found in examples directory of the source distribution or browsed at http://ffnet.sourceforge.net. -- Marek Wojciechowski -- http://mail.python.org/mailman/listinfo/python-announce-list Support the Python Software Foundation: http://www.python.org/psf/donations.html