Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!usc!rutgers!caip.rutgers.edu!boubez From: boubez@caip.rutgers.edu (Toufic Boubez) Newsgroups: comp.ai.neural-nets Subject: Simulators Keywords: back-prop, public domain Message-ID: Date: 9 Jan 91 21:39:18 GMT Organization: Rutgers Univ., New Brunswick, N.J. Lines: 14 This is probably one of the most asked questions on this group, but I don't know where else to get this information (unless there's an archive). I am looking for a simulator (preferably public domain) for back-propagation training. I need to have the possibility of user-defined activation function (ie not necessarily sigmoid) and flexibility in the selection of the input vectors. Any help on this would be greatly appreciated. Thanks. toufic R 2 4 |_|_| Toufic Boubez | | | boubez@caip.rutgers.edu 1 3 5 CAIP Center, Rutgers University