From kaiser@ira.uka.de Tue Oct 27 00:47:37 1992 Received: from iraun1.ira.uka.de by toadflax.cs.ucdavis.edu (4.1/UCD.CS.2.0) id AA07355; Tue, 27 Oct 92 00:47:23 PST Message-Id: <9210270847.AA07355@toadflax.cs.ucdavis.edu> Received: from ira.uka.de by iraun1.ira.uka.de with SMTP (PP) id <08628-0@iraun1.ira.uka.de>; Tue, 27 Oct 1992 09:46:25 +0100 Date: Tue, 27 Oct 92 9:46:11 MET From: kaiser@ira.uka.de Subject: Announce-Synworks To: announce@cs.ucdavis.edu To: Status: RO Hi Dan ! I just uploaded the new demonstration version of SynWorks (1st Kick 1.3 compatible version on Fish 510) to a few sites. Please find the announcement for c.s.a.announce below. If you have any questions, just contact me. Best regards, Michael ------------------------------------------------------------------------------ Michael Kaiser / Only my personal opinions Universitaet Karlsruhe Institut fuer Prozessrechentechnik und Robotik Internet : kaiser@ira.uka.de Postfach 6980 Tel. : +49 721 608-4051 D-7500 Karlsruhe 1, FR Germany FAX : +49 721 606-740 ------------------------------------------------------------------------------ Privat: Rintheimer Strasse 59 // Have you D-7500 Karlsruhe 1, FR Germany // hugged \\ // your Tel. : (+49) (721) 61 18 19 \X/ Amiga today ? Komm. : Michael_Kaiser@KA.maus.de [A3000/20/260] ------------------------------------------------------------------------------ "Die schiessen auf mein schoenes Auto ... !" (Canardo) ------------------------------------------------------------------------------ ---------------- for c.s.a.announce ------------------------- TITLE SynWorks - A design, training, test, and visualization environment for neural networks. VERSION 2.0, Oct. 26th, 1992 DESCRIPTION SynWorks is a fully integrated environment for design, training and test of neural networks. Currently, it supports 11 different network types, the networks' sizes are only limited by the amount of memory available. SynWorks provides instruments to watch and track (to disk) all important network parameters, all kinds of errors and of course, all input and output values provided to or by the network. All network parameters can be edited, and, starting from standard networks, custom networks can be created by adding links and neurons, modifying all functions (learn, transfer, error, evaluation). Input/output behaviour can easily be specified in terms of ranges, sources, and targets. Network display modes include structural, error-related, change-related, weight-related and memory related displays. All displays provide point- and click interfaces to the displayed parameters and are available simultaneously (watch chipmem !). All networks can be printed in four different modes, giving a textual, structural and two different descriptions on the network's weight map. SynWorks also provides a context-sensitive on-line help system that includes descriptions of all actions and important components, linked together via cross-references and easily accessible via buttons and hot-keys. Also, SynWorks features a full AREXX-interface that allows to define macros for internal use as well as using a network as part of a larger system, execute demonstrations etc.. The full version of SynWorks includes the following: 4 disks, containing - SynWorks 2.0 neural network design and development tool, plain 68000 version as well as 68020/68881++ version. - Example networks for tutorial - SynCode.lib, library to be linked to C programs to allow easy use of networks in user C programs (networks appear as subroutines) - SynCode programming examples, comprising Car control, character recognition, decision table execution, ECG evaluation. - SynTools 1.1, last version of a data display and processing tool (not supporting Kickstart 2.0x special features YET), upgradable to SynTools 2.0 (coming soon) and very useful for display and annotation of training data, also for evaluation of results. Printed manuals: - SynWorks reference manual, including SynCode reference and tutorial on both SynWorks and SynCode - Introduction to neural network theory - SynTools reference manual (Version 1.1) FEATURES 12 different standard network models 5 different possibilities to display network (simultaneously) 4 different possibilities to print network (standard WB printer, colour printing supported) 24 different instruments to watch and track the network's behaviour 53 AREXX commands give full external control over SynWorks. On-line context sensitive help system, supports keyword tracking. Supports all resolutions higher than or equal to 640 x 400 with at least two bitplanes (incl. A 2024, Productivity, AGA). GUI according to User Interface Style Guide. Version for 68020/68881 and up available. C programming interface available. REQUIREMENTS Amiga 500, 1000, 2000, 2500, 3000, 4000, 1.5 MByte RAM, Kickstart 2.04 and up. Harddisk recommended, FPU (special program version) highly recommended, Display enhancer/FF/AGA recommended. AUTHOR Michael Kaiser, kaiser@ira.uka.de DigiBrain - Software for Science (for the amazing Amiga :-)) Rintheimer Strasse 59 D 7500 Karlsruhe, FRG Phone : (+49) (721) 61 18 19 THANX Thanks to H*wlett P*ckard for providing a nice environment to write my master's thesis, also for producing D*sk- and L*serJets to print nice manuals. Thanks to Georg Hessmann for PasTeX (though I had to adapt makeindex myself :-)) For people in Europe: This package has been referenced in ATP (Automatisierungstechnische Praxis), Issue 9/92. AVAILABILITY wuarchive.wustl.edu (128.252.135.4): /systems/amiga/incoming/misc/synworksdemo.lha /systems/amiga/science/synworksdemo.lh amiga.physik.unizh.ch (130.60.80.80) and other Aminet sites: /amiga/new/synworksdemo.lha /amiga/misc/sci/synworksdemo.lha (For amiga.physik.unizh.ch, the aminet directory is /amiga; for others, try /aminet if you don't know) iraun1.ira.uka.de (129.13.10.90): /incoming/synworksdemo.lha /pub/systems/amiga/synworksdemo.lha DISTRIBUTABILITY Shareware, the ftp archive contains a demonstration version with certain features disabled. Users of versions 1.0, 1.1 and 1.2 will be directly informed about upgrade possibilities, all new users can get the full version as described above directly from the author.