********************************************************************** SNNS (Stuttgart Neural Network Simulator) Version 4.1 available ********************************************************************** The new version 4.1 of SNNS is available now. ********************************************************************** New features of SNNSv4.1 ********************************************************************** Version 4.1 of SNNS features the following improvements and extensions over the earlier version 4.0: * New batch execution language batchman * Integration of the genetic algorithm tool Enzo. Enzo is available as seperate tar file on our ftp-server at the same location as SNNS. For all enquiries about Enzo please contact enzo-request@ira.uka.de. * Improved window handling. On re-opening of a SNNS window it gets put on top, instead of issuing an error message. * new learning algorithm 'scaled conjugated gradient' (SCG) * The parameter lists in the control panel adapt to the number of paramters required, i.e. all widgets present need to be filled out. * WinSNNS, a MS-Windows front-end to SNNS batch execution on unix workstations. WinSNNS is NOT part of our official SNNS distribution! It can be found at http://www.lans.ece.utexas.edu/winsnns.html. Please contact ghosh@pine.ece.utexas.edu for more information. * optional parameter `Teacher-Forcing' for Jordan networks introduced. * validation now possible for BPTT networks * Extensive debugging: -- Seg-fault when trying to train a network without output units -- Seg-fault when pressing the info button without loaded patterns -- wrong feedback loops in associative memory nets deleted -- wrong activation functions in associative memory when constructed with bignet -- wrong initialization function in kohonen networks when constructed with bignet -- Wrong error computation in Hebbian learning -- Wrong error computation of analyze function band -- Wrong MSE computation for validation -- Better font size adaption of label widgets -- Pruning now allows validation with 0 cycles -- GRAPH panel could sometimes not be closed -- Wrong scanning of update parameters in snnsbat -- Error in the manual: Missing parameter of BackpropWeightDecay ********************************************************************** Machine architectures on which SNNSv4.1 is available ********************************************************************** We have tested SNNSv4.1 on the following machines and operating systems: machine type OS user interface with SUN Sparc ELC, SS2, SS10 SunOS 4.1.3 X11R5, X11R6, OW 3.0 SUN Sparc SS10, SS20 Solaris 2.4 X11R5, X11R6, OW 3.0 SGI Indigo II IRIX 5.1, 5.2 X11R5 DECstation 5000 Ultrix V4.2 X11R5 DEC Alpha Workstation OSF 1.1 X11R5 IBM RS 6000/320, 320H, 520, AIX V3.2 X11R5 HP 9000/720, 730 HP/UX 9.0.1 X11R5 IBM-PC 80486, Pentium Linux X11R5 Our parallel versions of SNNS are only available for research partners with whom we have sponsored joint research projects. These parallel versions include Neurocomputer Adaptive Solutions CNAPS serverII SIMD computer MasPar MP-1, MP-2 MIMD computer Intel Paragon XP/S5, Connection Machine CM-5 ********************************************************************** How to obtain SNNSv4.1 ********************************************************************** The SNNS simulator can be obtained via anonymous ftp from host ftp.informatik.uni-stuttgart.de (129.69.211.2) in the subdirectory /pub/SNNS as file SNNSv4.1.tar.Z (2.60 MB) or in zipped form as file SNNSv4.1.tar.gz (1.60 MB) Be sure to set the ftp mode to binary before transmission of the files. Also watch out for possible higher version numbers, patches or Readme files in the above directory /pub/SNNS . After successful transmission of the file move it to the directory where you want to install SNNS, uncompress and extract the file with the Unix command tar xvfZ SNNSv4.1.tar.Z The SNNS distribution includes full source code, installation procedures for supported machine architectures and some simple examples of trained networks. The PostScript version of the user manual can be obtained as file SNNSv4.1.Manual.ps.Z (1.61 MB) or SNNSv4.1.Manual.ps.gz (1.05 MB) or in 15 parts as files SNNSv4.1.Manual.part01.ps.Z ... SNNSv4.1.Manual.part15.ps.Z These parts are all under 1 MB in size when uncompressed and should be printable on any PostScript printer.Again remember to set the ftp mode to binary before transmission of the file(s). There is also an Implementation Manual available as file SNNSv4.1.Implem.ps.Z (0.24 MB) and a set of extension chapters for those users who just printed the manual of version 4.1 in file SNNSv4.1.Manual.Extensions.ps.Z (0.30MB) More information about SNNS as well as a html version of the manual can be found at http://vasarely.informatik.uni-stuttgart.de/snns/snns.html Unfortunately are we momentarily unable to provide any printed/bound version of the manual until further notice.