Archive-name: ai-faq/neural-nets/part6 Last-modified: 2002-03-28 URL: ftp://ftp.sas.com/pub/neural/FAQ6.html Maintainer: saswss@unx.sas.com (Warren S. Sarle)
This is part 6 (of 7) of a monthly posting to the Usenet newsgroup comp.ai.neural-nets. See the part 1 of this posting for full information what it is all about.
------------------------------------------------------------------------
Note for future submissions: Please restrict product descriptions to a maximum of 60 lines of 72 characters, in either plain-text format or, preferably, HTML format. If you include the standard header (name, company, address, etc.), you need not count the header in the 60 line maximum. Please confine your HTML to features that are supported by primitive browsers, especially NCSA Mosaic 2.0; avoid tables, for example--use <pre> instead. Try to make the descriptions objective, and avoid making implicit or explicit assertions about competing products, such as "Our product is the *only* one that does so-and-so." The FAQ maintainer reserves the right to remove excessive marketing hype and to edit submissions to conform to size requirements; if he is in a good mood, he may also correct your spelling and punctuation.
The following simulators are described below:
Product: BrainMaker, BrainMaker Pro
Company: California Scientific Software
Address: 10024 Newtown rd, Nevada City, CA, 95959 USA
Phone: 800 284-8112, 530 478 9040
Fax: 530 478 9041
URL: http://www.calsci.com/
Basic capabilities: train backprop neural nets
Operating system: Windows, Mac
System requirements:
Approx. price: $195, $795
BrainMaker Pro 3.7 (DOS/Windows) $795
Gennetic Training add-on $250
BrainMaker 3.7 (DOS/Windows/Mac) $195
Network Toolkit add-on $150
BrainMaker 3.7 Student version (quantity sales only, about $38 each)
BrainMaker Pro CNAPS Accelerator Board $8145
Introduction To Neural Networks book $30
30 day money back guarantee, and unlimited free technical support.
BrainMaker package includes:
The book Introduction to Neural Networks
BrainMaker Users Guide and reference manual
300 pages, fully indexed, with tutorials, and sample networks
Netmaker
Netmaker makes building and training Neural Networks easy, by
importing and automatically creating BrainMaker's Neural Network
files. Netmaker imports Lotus, Excel, dBase, and ASCII files.
BrainMaker
Full menu and dialog box interface, runs Backprop at 3,000,000 cps
on a 300Mhz Pentium II; 570,000,000 cps on CNAPS accelerator.
---Features ("P" means is available in professional version only):
MMX instruction set support for increased computation speed,
Pull-down Menus, Dialog Boxes, Programmable Output Files,
Editing in BrainMaker, Network Progress Display (P),
Fact Annotation, supports many printers, NetPlotter,
Graphics Built In (P), Dynamic Data Exchange (P),
Binary Data Mode, Batch Use Mode (P), EMS and XMS Memory (P),
Save Network Periodically, Fastest Algorithms,
512 Neurons per Layer (P: 32,000), up to 8 layers,
Specify Parameters by Layer (P), Recurrence Networks (P),
Prune Connections and Neurons (P), Add Hidden Neurons In Training,
Custom Neuron Functions, Testing While Training,
Stop training when...-function (P), Heavy Weights (P),
Hypersonic Training, Sensitivity Analysis (P), Neuron Sensitivity (P),
Global Network Analysis (P), Contour Analysis (P),
Data Correlator (P), Error Statistics Report,
Print or Edit Weight Matrices, Competitor (P), Run Time System (P),
Chip Support for Intel, American Neurologics, Micro Devices,
Genetic Training Option (P), NetMaker, NetChecker,
Shuffle, Data Import from Lotus, dBASE, Excel, ASCII, binary,
Finacial Data (P), Data Manipulation, Cyclic Analysis (P),
User's Guide quick start booklet,
Introduction to Neural Networks 324 pp book
Product: SAS Enterprise Miner Solution
In USA: In Europe:
Company: SAS Institute, Inc. SAS Institute, European Office
Address: SAS Campus Drive Neuenheimer Landstrasse 28-30
Cary, NC 27513 P.O.Box 10 53 40
USA D-69043 Heidelberg
Germany
Phone: (919) 677-8000 (49) 6221 4160
Fax: (919) 677-4444 (49) 6221 474 850
URL: http://www.sas.com/
To find the addresses and telephone numbers of other SAS Institute
offices, including those outside the USA and Europe, connect your web
browser to
http://www.sas.com/offices/intro.html.
Enterprise Miner is an integrated software product that provides an end-to-end business solution for data mining based on SEMMA methodology (Sample, Explore, Modify, Model, Assess). Statistical tools include clustering, decision trees, linear and logistic regression, and neural networks. Data preparation tools include outlier detection, variable transformations, random sampling, and the partitioning of data sets (into training, test, and validation data sets). Advanced visualization tools enable you to quickly and easily examine large amounts of data in multidimensional histograms, and to graphically compare modeling results.
The neural network tool includes multilayer perceptrons, radial basis functions, statistical versions of counterpropagation and learning vector quantization, a variety of built-in activation and error functions, multiple hidden layers, direct input-output connections, categorical variables, standardization of inputs and targets, and multiple preliminary optimizations from random initial values to avoid local minima. Training is done by powerful numerical optimization algorithms instead of tedious backprop.
Product: NeuralWorks Professional II Plus
NeuralWorks Predict
Company: NeuralWare
Adress: 230 East Main Street
Suite 200
Carnegie, PA 15106-2700
Phone: (412) 278-6280
FAX: (412) 278-6289
Email: sales@neuralware.com
URL: http://www.neuralware.com/
NeuralWorks Professional II/PLUS is a comprehensive neural
network development environment. Professional II/PLUS is available for
UNIX, Linux, and Windows operating systems on a variety of hardware
platforms; data and network files are fully interchangeable. The
Professional II/PLUS package contains comprehensive documentation that
addresses the entire neural network development and deployment process,
including a tutorial, a guide to neural computing, standard and advanced
reference manuals, and platform-specific installation and user guides.
NeuralWare's proprietary InstaNet facility allows quick generation of a neural network based on any one of 28 standard neural network architectures described in neural network literature. After a network is created, all parameters associated with it can be directly modified to more closely reflect the problem domain. Professional II/PLUS includes advanced features such as performance measure-based methods to inhibit over-fitting; automatic optimization of hidden layer size and the ability to prune hidden units; and an Explain facility that indicates which network inputs most influence network outputs.
NeuralWorks Predict is an integrated tool for rapidly creating and deploying prediction and classification applications. Predict combines neural network technology with genetic algorithms, statistics, and fuzzy logic to automatically find solutions for a wide range of problems. Predict incorporates years of modeling and analysis experience gained from working with customers faced with a wide variety of analysis and interpretation problems.
Predict requires no prior knowledge of neural networks. With only minimal user involvement it addresses the issues associated with building robust models from available empirical data. Predict analyzes input data to identify appropriate transforms, partitions the input data into training and test sets, selects relevant input variables, and then constructs, trains, and optimizes a neural network tailored to the problem. For advanced users, Predict also offers direct access to all key training and network parameters.
The Mathworks Inc. 3 Apple Hill Drive Natck, MA 01760 Phone: 508-647-7000 Fax: 508-647-7001 URL: http://www.mathworks.com/products/neuralnet/The Neural Network Toolbox is a powerful collection of MATLAB functions for the design, training, and simulation of neural networks. It supports a wide range of network architectures with an unlimited number of processing elements and interconnections (up to operating system constraints). Supported architectures and training methods include: supervised training of feedforward networks using the perceptron learning rule, Widrow-Hoff rule, several variations on backpropagation (including the fast Levenberg-Marquardt algorithm), and radial basis networks; supervised training of recurrent Elman networks; unsupervised training of associative networks including competitive and feature map layers; Kohonen networks, self-organizing maps, and learning vector quantization. The Neural Network Toolbox contains a textbook-quality Users' Guide, uses tutorials, reference materials and sample applications with code examples to explain the design and use of each network architecture and paradigm. The Toolbox is delivered as MATLAB M-files, enabling users to see the algorithms and implementations, as well as to make changes or create new functions to address a specific application.
Contact: ARD Corporation,
9151 Rumsey Road, Columbia, MD 21045, USA
propagator@ard.com
Easy to use neural network training package. A GUI implementation of
backpropagation networks with five layers (32,000 nodes per layer).
Features dynamic performance graphs, training with a validation set,
and C/C++ source code generation.
For Sun (Solaris 1.x & 2.x, $499),
PC (Windows 3.x, $199)
Mac (System 7.x, $199)
Floating point coprocessor required, Educational Discount,
Money Back Guarantee, Muliti User Discount
See http://www.cs.umbc.edu/~zwa/Gator/Description.html
Windows Demo on:
nic.funet.fi /pub/msdos/windows/demo
oak.oakland.edu /pub/msdos/neural_nets
gatordem.zip pkzip 2.04g archive file
gatordem.txt readme text file
Product: NeuroForecaster(TM)/Genetica 4.1a
Contact: Accel Infotech (S) Pte Ltd
648 Geylang Road
Republic of Singapore 1438
Phone: +65-7446863, 3366997
Fax: +65-3362833
URL: http://web.singnet.com.sg/~midaz/
Neuroforecaster 4.1a for Windows is priced at US$1199 per single user license. Please email accel@technet.sg for order form.
NeuroForecaster is a user-friendly ms-windows neural network program
specifically designed for building sophisticated and powerful forecasting
and decision-support systems (Time-Series Forecasting, Cross-Sectional
Classification, Indicator Analysis)
Features:
530 Fifth Avenue; New York, NY 10036; USA; Tel.: 001-212-398-7955 URL: http://asweb.artsci.uc.edu/classics/nestor/nestor.html Founders: Dr. Leon Cooper (having a Nobel Prize) and Dr. Charles Elbaum (Brown University). Neural Network Models: Adaptive shape and pattern recognition (Restricted Coulomb Energy - RCE) developed by NESTOR is one of the most powerfull Neural Network Model used in a later products. The basis for NESTOR products is the Nestor Learning System - NLS. Later are developed: Character Learning System - CLS and Image Learning System - ILS. Nestor Development System - NDS is a development tool in Standard C - a powerfull PC-Tool for simulation and development of Neural Networks. NLS is a multi-layer, feed forward system with low connectivity within each layer and no relaxation procedure used for determining an output response. This unique architecture allows the NLS to operate in real time without the need for special computers or custom hardware. NLS is composed of multiple neural networks, each specializing in a subset of information about the input patterns. The NLS integrates the responses of its several parallel networks to produce a system response. Minimized connectivity within each layer results in rapid training and efficient memory utilization- ideal for current VLSI technology. Intel has made such a chip - NE1000.
Product: NeuroShell Predictor, NeuroShell Classifier,
NeuroShell Run-Time Server, NeuroShell Trader,
NeuroShell Trader Professional, NeuroShell 2,
GeneHunter, NeuroShell Engine
Company: Ward Systems Group, Inc.
Address: Executive Park West
5 Hillcrest Drive
Frederick, MD 21702
USA
Phone: 301 662-7950
FAX: 301 662-5666
Email: WardSystems@msn.com
URL: http://www.wardsystems.com
Ward Systems Group Product Descriptions:
Contact us for a free demo diskette and Consumer's Guide to Neural Networks.
Product: Neuralyst Version 1.4;
Company: Cheshire Engineering Corporation;
Address: 650 Sierra Madre Villa, Suite 201, Pasedena CA 91107;
Phone: 818-351-0209;
Fax: 818-351-8645;
URL: http://www.cheshireeng.com/Neuralyst/
Basic capabilities: training of backpropogation neural nets.
Operating system: Windows or Macintosh running Microsoft Excel
Spreadsheet. Neuralyst is an add-in package for Excel. Approx. price:
$195 for windows or Mac.
Please visit our home on the World Wide Web: www.partek.com
Partek Incorporated
5988 Mid Rivers Mall Dr.
St. Charles, MO 63304
voice: 314-926-2329
fax: 314-441-6881
email: info@partek.com
http://www.partek.com/
Product: NeuroSolutions
Company: NeuroDimension, Inc.
Address: 1800 N. Main St., Suite D4
Gainesville FL, 32609
Phone: (800) 634-3327 or (352) 377-5144
FAX: (352) 377-9009
Email: info@nd.com
URL: http://www.nd.com/
Operating System: Windows 95/98/Me/NT/2000
Price: $195 - $1995 (educational discounts available)
NeuroSolutions is a highly graphical neural network development tool for
Windows 95/98/Me/NT/2000. This leading edge software combines a modular,
icon-based network design interface with an implementation of advanced
learning procedures, such as recurrent backpropagation, backpropagation
through time and genetic optimization. The result is a virtually
unconstrained environment for designing neural networks for research or
to solve real-world problems.
Download a free evaluation copy from http://www.nd.com/download.htm.
Vesta Services, Inc. 1001 Green Bay Rd, Suite 196 Winnetka, IL 60093 Phone: (708) 446-1655 E-Mail: VestaServ@aol.comTrial Version Available: http://www.qnetv2k.com/
Vesta Services announces Qnet for Windows Version 2.0. Qnet is an advanced neural network modeling system that is ideal for developing and implementing neural network solutions under Windows. The use of neural network technology has grown rapidly over the past few years and is being employed by an increasing number of disciplines to automate complex decision making and problem solving tasks. Qnet Version 2 is a powerful, 32-bit, neural network development system for Windows NT, Windows 95 and Windows 3.1/Win32s. In addition its development features, Qnet automates access and use of Qnet neural networks under Windows.
Qnet neural networks have been successfully deployed to provide solutions in finance, investing, marketing, science, engineering, medicine, manufacturing, visual recognition... Qnet's 32-bit architecture and high-speed training engine tackle problems of large scope and size. Qnet also makes accessing this advanced technology easy. Qnet's neural network setup dialogs guide users through the design process. Simple copy/paste procedures can be used to transfer training data from other applications directly to Qnet. Complete, interactive analysis is available during training. Graphs monitor all key training information. Statistical checks measure model quality. Automated testing is available for training optimization. To implement trained neural networks, Qnet offers a variety of choices. Qnet's built-in recall mode can process new cases through trained neural networks. Qnet also includes a utility to automate access and retrieval of solutions from other Windows applications. All popular Windows spreadsheet and database applications can be setup to retrieve Qnet solutions with the click of a button. Application developers are provided with DLL access to Qnet neural networks and for complete portability, ANSI C libraries are included to allow access from virtually any platform.
Qnet for Windows is being offered at an introductory price of $199. It is available immediately and may be purchased directly from Vesta Services. Vesta Services may be reached at (voice) (708) 446-1655; (FAX) (708) 446-1674; (e-mail) VestaServ@aol.com; (mail) 1001 Green Bay Rd, #196, Winnetka, IL 60093
NeuroLab is a block-diagram-based neural network library for Extend
simulation software (developed by Imagine That, Inc.). The library
aids the understanding, designing and simulating of neural network
systems. The library consists of more than 70 functional blocks for
artificial neural network implementation and many example models in
several professional fields.The package provides icon-based
functional blocks for easy implementation of simulation models.
Users click, drag and connect blocks to construct a neural network
and can specify network parameters--such as back propagation methods,
learning rates, initial weights, and biases--in the dialog boxes of
the functional blocks.
Users can modify blocks with the Extend
model-simulation scripting language, ModL, and can include compiled
program modules written in other languages using XCMD and XFCN
(external command and external function) interfaces and DLL (dynamic
linking library) for Windows. The package provides many kinds of
output blocks to monitor neural network status in real time using
color displays and animation and includes special blocks for control
application fields. Educational blocks are also included for people
who are just beginning to learn about neural networks and their
applications.
The library features various types of neural networks
--including Hopfield, competitive, recurrent, Boltzmann machine,
single/multilayer feed-forward, perceptron, context, feature map,
and counter-propagation-- and has several back-propagation options:
momentum and normalized methods, adaptive learning rate, and
accumulated learning.
The package runs on Macintosh II or higher (FPU
recommended) with system 6.0.7 or later and PC compatibles (486 or
higher recommended) with Windows 3.1 or later, and requires 4Mbytes
of RAM. Models are transferable between the two platforms. NeuroLab
v1.2 costs US$495 (US$999 bundled with Extend v3.1). Educational and
volume discounts are available.
A free demo can be downloaded by
ftp://ftp.mikuni.com/pub/neurolab or
http://www.mikuni.com/.
Orders, questions or suggestions can be sent by e-mail to
neurolab-info@mikuni.com.
Names: havBpNet++
havFmNet++
havBpNet:J
Company: hav.Software
P.O. Box 354
Richmond, Tx. 77406-0354 - USA
Phone: (281) 341-5035
Email: hav@hav.com
Web: http://www.hav.com/
Supports all standard network parameters (learning-rate, momentum, Cascade- coefficient, weight-decay, batch training, etc.). Includes 5 activation-functions (Linear, Logistic-sigmoid, Hyperbolic-tangent, Sin and Hermite) and 3 error-functions (e^2, e^3, e^4). Also included is a special scaling utility for data with large dynamic range.
Several data-handling classes are also included. These classes, while not required, may be used to provide convenient containers for training and consultation data. They also provide several normalization/de-normalization methods.
havBpNet++ is delivered as fully documented source + 200 pg User/Developer Manual. Includes a special DLL version. Includes several example trainers and consulters with data sets. Also included is a fully functioning copy of the havBpETT demo (with network-save enabled).
NOTE: a freeware version (Save disabled) of the havBpETT demo may be downloaded from the hav.Software home-page: http://www.neosoft.com/~hav or by anonymous ftp from ftp://ftp.neosoft.com/pub/users/h/hav/havBpETT/demo2.exe.
Platforms: Tested platforms include - PC (DOS, Windows-3.1, NT, Unix),
HP (HPux), SUN (Sun/OS), IBM (AIX), SGI (Irix).
Source and Network-save files portable across platforms.
Licensing: havBpNet++ is licensed by number of developers.
A license may be used to support development on any number
and types of cpu's.
No Royalties or other fees (except for OEM/Reseller)
Price: Individual $50.00 - one developer
Site $500.00 - multiple developers - one location
Corporate $1000.00 - multiple developers and locations
OEM/Reseller quoted individually
(by American Express, bank draft and approved company PO)
Media: 3.5-inch floppy - ascii format (except havBpETT which is in PC-exe
format).
havFmNet++ may be used for both stand-alone and embedded network training and consultation applications. A simple Layer-based API, along with no restrictions on layer-size or number of layers, makes it easy to build single- layer nets or much more complex multiple-layer topologies. havFmNet++ is fully compatible with havBpNet++ which may be used for pre- and post- processing.
Supports all standard network parameters (learning-rate, momentum, neighborhood, conscience, batch, etc.). Uses On-Center-Off-Surround training controlled by a sombrero form of Kohonen's algorithm. Updates are controllable by three neighborhood related parameters: neighborhood-size, block-size and neighborhood-coefficient cutoff. Also included is a special scaling utility for data with large dynamic range.
Several data-handling classes are also included. These classes, while not required, may be used to provide convenient containers for training and consultation data. They also provide several normalization/de-normalization methods.
havFmNet++ is delivered as fully documented source plus 200 pg User/Developer Manual. Includes several example trainers and consulters with data sets.
Platforms: Tested platforms include - PC (DOS, Windows-3.1, NT, Unix),
HP (HPux), SUN (Sun/OS), IBM (AIX), SGI (Irix).
Source and Network-save files portable across platforms.
Licensing: havFmNet++ is licensed by number of developers.
A license may be used
to support development on any number and types of cpu's.
No Royalties or other fees (possible exception for OEM).
Price: Individual $50.00 - one developer
Site $500.00 - multiple developers - one location
Corporate $1000.00 - multiple developers and locations
OEM/Reseller quoted individually
(by American Express, bank draft and approved company PO)
Media: 3.5-inch floppy - ascii format
Supports all standard network parameters (learning-rate, momentum, Cascade-coefficient, weight-decay, batch training, error threshold, etc.). Includes 5 activation-functions (Linear, Logistic-sigmoid, Hyperbolic-tangent, Sin and Hermite) and 3 error-functions (e^2, e^3, e^4). Also included is a special scaling utility for data with large dynamic range.
Several data-handling classes are also included. These classes, while not required, may be used to provide convenient containers for training and consultation data. They also provide several normalization/de-normalization methods.
Platforms: Java Virtual Machines - 1.0 and later
Licensing: No Royalties or other fees (except for OEM/Reseller)
Price: Individual License is $55.00
Site, Corporate and OEM/Reseller also available
Media: Electronic distribution only.
BioComp Systems, Inc. introduced version 1.0 of the NGO in January of 1995 and now proudly announces version 2.0. With version 2.0, the NGO is now equipped for predicting time-based information such as product sales, financial markets and instruments, process faults, etc., in addition to its current capabilities in functional modeling, classification, and diagnosis.
While the NGO embodies sophisticated genetic algorithm search and neural network modeling technology, it has a very easy to use GUI interface for Microsoft Windows. You don't have to know or understand the underlying technology to build highly effective financial models. On the other hand, if you like to work with the technology, the NGO is highly configurable to customize the NGO to your liking.
Key new features of the NGO include:
With version 2.0, the NGO is now available as a full 32 bit application for Windows '95 and Windows NT to take advantage of the 32 bit preemptive multitasking power of those platforms. A 16 bit version for Windows 3.1 is also available. Customized professional server based systems are also available for high volume automated model generation and prediction. Prices start at $195.
BioComp Systems, Inc. Overlake Business Center 2871 152nd Avenue N.E. Redmond, WA 98052, USA 1-800-716-6770 (US/Canada voice)=20 1-206-869-6770 (Local/Int'l voice) 1-206-869-6850 (Fax) http://www.bio-comp.com. biocomp@biocomp.seanet.com 70673.1554@compuserve.com
An ALN consists of linear functions with adaptable weights at the leaves of a tree of maximum and minimum operators. The tree grows automatically during training: a linear piece splits if its error is too high. The function computed by an ALN is piecewise linear and continuous, and can approximate any continuous function to any required accuracy. Statistics are reported on the fit of each linear piece to test data.
The DLE has been very successful in predicting electrical power loads in the Province of Alberta. The 24-hour ahead load for all of Alberta (using seven weather regions) was predicted using a single ALN. Visit http://www.dendronic.com/applications.htm to learn about other successful applications to ATM communication systems, walking prostheses for persons with incomplete spinal cord injury, and many other areas.
Operating Systems: Windows NT 4.0, 95 and higher.
Price: Prices for the SDK start at $3495 US for a single seat, and are negotiable for embedded learning systems. A runtime non-learning system can be distributed royalty-free.
The power of the DLE can be tried out using an interactive spreadsheet program, ALNBench. ALNBench is free for research, education and evaluation purposes. The program can be downloaded from http://www.dendronic.com/beta.htm (Please note the installation key given there!)
For further information please contact:
William W. Armstrong PhD, President Dendronic Decisions Limited 3624 - 108 Street, NW Edmonton, Alberta, Canada T6J 1B4 Email: arms@dendronic.com URL: http://www.dendronic.com/ Tel. +1 403 421 0800 (Note: The area code 403 changes to 780 after Jan. 25, 1999)
Platform: Windows 3.* Company: Universal Problem Solvers, Inc. WWW-Site (UPSO): http://www.alberts.com/authorpages/00002375/prod_262.htm or FTP-Site (FREE Demo only): ftp.coast.net, in Directory: SimTel/win3/neurlnet, File: tdl11-1.zip and tdl11-2.zip Cost of complete program: US$20 + (US$3 Shipping and Handling).The purpose of TDL is to provide users of neural networks with a specific platform to conduct pattern recognition tasks. The system allows for the fast creation of automatically constructed neural networks. There is no need to resort to manually creating neural networks and twiddling with learning parameters. TDL's Wizard can help you optimize pattern recognition accuracy. Besides allowing the application user to automatically construct neural network for a given pattern recognition task, the system supports trans-dimensional learning. Simply put, this allows one to learn various tasks within a single network, which otherwise differ in the number of input stimuli and output responses utilized for describing them. With TDL it is possible to incrementally learn various pattern recognition tasks within a single coherent neural network structure. Furthermore, TDL supports the use of semi-weighted neural networks, which represent a hybrid cross between standard weighted neural networks and weightless multi-level threshold units. Combining both can result in extremely compact network structures (i.e., reduction in connections and hidden units), and improve predictive accuracy on yet unseen patterns. Of course the user has the option to create networks which only use standard weighted neurons.
System Highlights:
Product: Neuframe v.4 - ActiveX Components
Company: Neusciences
Address: Unit 2
Lulworth Business Centre
Totton
Southampton
UK
SO40 3WW
Phone: +44 023 80 664011
Email: sales@neusciences.com
URL: http://www.neusciences.com
Neuframe is an easy-to-use, visual, object-oriented approach to problem
solving, allowing the user to embed intelligent technologies within
their applications. Neuframe provides features that enable businesses
to investigate and apply Intelligence Technologies from an initial low
cost experimentation platform, through to the building of embedded
implementations using software components. Includes:
Recommended Configuration - Windows 9X, NT4 or 2000, Pentium 200 with 64Mb Ram
Price: Commercial £1295 - Educational £777 (pounds sterling)
ActiveX Components
KMeans, Linear Regression, Data Encoder: Price £150 each (pounds sterling)
Multi-Layered Perceptron, Radial Basis Function, Projection Pursuit Regression, Kohonen: Price £350 each (pounds sterling)
Product: OWL Neural Network Library (TM)
Company: HyperLogic Corporation
Address: PO Box 300010
Escondido, CA 92030
USA
Phone: +1 619-746-2765
Fax: +1 619-746-4089
Email: prodinfo@hyperlogic.com
URL: http://www.hyperlogic.com/owl.html
The OWL Neural Network Library provides a set of popular networks in
the form of a programming library for C or C++ software development.
The library is designed to support engineering applications as well as
academic research efforts. A common programming interface allows consistent access to the various paradigms. The programming environment consists of functions for creating, deleting, training, running, saving, and restoring networks, accessing node states and weights, randomizing weights, reporting the complete network state in a printable ASCII form, and formatting detailed error message strings.
The library includes 20 neural network paradigms, and facilitates the construction of others by concatenation of simpler networks. Networks included are:
Supported Environments:
The object code version of OWL is provided on MS-DOS format diskettes
with object libraries and makefiles for both Borland and Microsoft C.
An included Windows DLL supports OWL development under Windows. The
package also includes Owgraphics, a mouseless graphical user interface
support library for DOS.
Both graphical and "stdio" example programs are included.
The Portable Source Code version of OWL compiles without change on
many hosts, including VAX, UINX, and Transputer. The source code
package includes the entire object-code package.
Price:
USA and Canada: (US) $295 object code, (US) $995 with source
Outside USA and Canada: (US) $350 object code, (US) $1050 with source
Shipping, taxes, duties, etc., are the responsibility of the customer.
Product: Neural Connection
Company: SPSS Inc.
Address: 444 N. Michigan Ave., Chicago, IL 60611
Phone: 1-800-543-2185
1-312-329-3500 (U.S. and Canada)
Fax: 1-312-329-3668 (U.S. and Canada)
Email: sales@spss.com
URL: http://www.spss.com
SPSS has offices worldwide. For inquiries outside the U.S. and Canada,
please contact the U.S. office to locate the office nearest you.
Operating system : Microsoft Windows 3.1 (runs in Windows 95)
System requirements: 386 pc or better, 4 MB memory (8MB recommended), 4 MB
free hard disk space, VGA or SVGA monitor, Mouse or other pointing device,
Math coprocessor strongly recommended
Price: $995, academic discounts available
Description
Neural Connection is a graphical neural network tool which uses an
icon-based workspace for building models for prediction, classification,
time series forecasting and data segmentation. It includes extensive
data management capabilities so your data preparation is easily done
right within Neural Connection. Several output tools give you the
ability to explore your models thoroughly so you understand your
results.
Modeling and Forecasting tools
* 3 neural network tools: Multi-Layer Perceptron, Radial Basis Function,
Kohonen network
* 3 statistical analysis tools: Multiple linear regression, Closest
class means classifier, Principal component analysis
Data Management tools
* Filter tool: transformations, trimming, descriptive statistics,
select/deselect variables for analysis, histograms
* Time series window: single- or multi-step prediction, adjustable step
size
* Network combiner
* Simulator
* Split dataset: training, validation and test data
* Handles missing values
Output Options
* Text output: writes ASCII and SPSS (.sav) files, actual values,
probabilities, classification results table, network output
* Graphical output: 3-D contour plot, rotation capabilties, WhatIf? tool
includes interactive sensititivity plot, cross section, color contour
plot
* Time series plot
Production Tools
* Scripting language for batch jobs and interactive applications
* Scripting language for building applications
Documentation
* User s guide includes tutorial, operations and algorithms
* Guide to neural network applications
Example Applications
* Finance - predict account attrition
* Marketing - customer segmentation
* Medical - predict length of stay in hospital
* Consulting - forecast construction needs of federal court systems
* Utilities - predict number of service requests
* Sales - forecast product demand and sales
* Science - classify climate types
Name: Pattern Recognition Workbench Expo/PRO/PRO+
Company: Unica Technologies, Inc.
Address: 55 Old Bedford Rd., Lincoln, MA 01773 USA
Phone, Fax: (617) 259-5900, (617) 259-5901
Email: unica@unica-usa.com
Basic capabilities:
Operating system: Windows 3.1, WFW 3.11, Windows 95, Windows NT (16- and 32-bit versions available)
System requirements: Intel 486+, 8+ MB memory, 5+ MB disk space
Approx. price: software starts at $995.00 (call for more info)
Solving Pattern Recognition Problems text book: $49.95
Money-back guarantee
Comments: Pattern Recognition Workbench (PRW) is a comprehensive environment/tool for solving pattern recognition problems using neural network, machine learning, and traditional statistical technologies. With an intuitive, easy-to-use graphical interface, PRW has the flexibility to address many applications. With features such as automated model generation (via input feature selection and algorithm parameter searches), experiment management, and statistical validation, PRW provides all the necessary tools from formatting and preprocessing your data to setting up, running, and evaluating experiments, to deploying your solution. PRW's automated model generation capability can generate literally hundreds of models, selecting the best ones from a thorough search space, ultimately resulting in better solutions!
* Definition of a forecast equation : *
Definition of the variable to forecast and explanatory variables.
Automatic harmonisation of the domains and periodicities involved in
the equation.
* Choice of a neuronal model associated with the forecasting equation : *
Automatic or manual definition of multi-layered architectures.
Temporal models with loop-backs of intermediate layers.
* Fine-tuning of a neuronal model by training *
Training by gradient back-propagation.
Automatic simplification of architectures.
Definition of training objectives by adaptation of the optimisation
criterion.
Definition of model form constraints.
Graphing of different error criteria.
* Analysis of a neuronal model: *
View of Hinton graph associated with each network layer.
Connection weight editing.
Calculation of sensitivity and elasticity of the variable to forecast,
in relation to the explanatory variables.
Calculation of the hidden series produced by the neural network.
* Neural Network-Based Forecasting *
Operational use of a neural network.
* Series Analysis *
Visualisation of a series curve. Editing of the series values.
Smoothing (simple, double, Holt & Winters)
Study of the predictability of a series (fractal dimension)
Comparison of two series. Visualisation of X-Y graphs.
WWW: http://www.trajan-software.demon.co.uk
Email: andrew@trajan-software.demon.co.uk
Tel: +44 191 388 5737. (8:00-22:00 GMT).
Features include:
Product: DataEngine, DataEngine ADL, DataEngine V.i
Company: MIT GmbH
Address: Promenade 9
52076 Aachen
Germany
Phone: +49 2408 94580
Fax: +49 2408 94582
EMail: mailto:info@mitgmbh.de
URL: http://www.mitgmbh.de
DataEngine is a software tool for data analysis implementing
Fuzzy Rule Based Systems, Fuzzy Cluster Methods, Neural Networks,
and Neural-Fuzzy Systems in combination with conventional methods
of mathematics, statistics, and signal processing.
DataEngine ADL enables you to integrate classifiers or controllers
developed with DataEngine into your own software environment. It
is offered as a DLL for MS/Windows or as a C++ library for various
platforms and compilers.
DataEngine V.i is an add-on tool for LabView (TM) that enables you
to integrate Fuzzy Logic and Neural Networks into LabView through
virtual instruments to build systems for data analysis as well as
for Fuzzy Control tasks.
[Note from FAQ maintainer: While this product explores some of the prerequisites of consciousness in an interesting way, it does not deal with deeper philosophical issues such as qualia.]
Questions to: Don Tveter, don@dontveter.com
Product: STATISTICA: Neural Networks version 4.0
Company: StatSoft, Inc.
Address: 2300 E. 14th St.
Tulsa, OK 74104
USA
Phone: (918) 749-1119
Fax: (918) 749-2217
Email: info@statsoft.com
URL: http://www.statsoft.com/
STATISTICA Neural Networks is a comprehensive application capable of
designing a wide range of neural network architectures, employing both
widely-used and highly-specialized training algorithms. STATISTICA
Neural Networks was developed by StatSoft, Inc., the makers of
STATISTICA software, and is available and supported through a world-wide
network of StatSoft subsidiaries.
The current version STATISTICA Neural Networks 4.0 offers features such as sophisticated training algorithms, an Intelligent Problem Solver that walks the user step-by-step through the analysis, a Neuro-Genetic Input Selection facility, a large selection of supplementary graphs and statistics (e.g., ROC, Response Surfaces, Sensitivity Analysis, Regression and Classification statistics), complete support for API (Application Programming Interface), and the ability to interface with STATISTICA data files and graphs.
STATISTICA Neural Networks includes traditional learning algorithms, such as back propagation and sophisticated training algorithms such as Conjugate Gradient Descent and Levenberg-Marquardt iterative procedures. Typically, choosing the right architecture of a neural network is a difficult and time-consuming "trial and error" process, but STATISTICA Neural Networks specifically does this for the user. STATISTICA Neural Networks features an Intelligent Problem Solver that utilizes heuristics and sophisticated optimization strategies to determine the best network architecture and walks the user step-by-step through the analysis. The Intelligent Problem Solver compares different network types (including Linear, Radial Basis Function, Multilayer Perceptron, and Bayesian networks), determines the number of hidden units, and chooses the Smoothing factor for Radial Basis Function networks.
The process of obtaining the right input variables in exploratory data analysis -- typically the case when neural networks are used -- also is facilitated by STATISTICA Neural Networks. Neuro-Genetic Input Selection procedures aid in determining the input variables that should be used in training the network. It uses an optimization strategy to compare the possible combinations of input variables to determine which set is most effective. STATISTICA Neural Networks offers complete API support so advanced users (or designers of corporate "knowledge seeking" or "data mining" systems) may be able to integrate the advanced computational engines of the Neural Networks module into their custom applications.
STATISTICA Neural Networks can be used as a stand-alone application or can interface directly with STATISTICA. It reads and writes STATISTICA data files and graphs.
Product: Braincel
Company: Promised Land Technologies
Address: 195 Church Street 11th Floor
New Haven, CT 06510
USA
Phone: (800) 243-1806 (Outside USA: (203) 562-7335)
Fax: (203) 624-0655
Email: gideon@miracle.net
URL: http://www.promland.com/
also see http://www.jurikres.com/catalog/ms_bcel.htm
Braincel is an add-in to Excel using a training method called
backpercolation.
Product: DESIRE/NEUNET
Company: G.A. and T.M. Korn Industrial Consultants
Address: 7750 South Lakeshore Road, # 15
Chelan, WA 98816
USA
Phone: (509) 687-3390
Email: gatmkorn@aol.com
URL: http://members.aol.com/gatmkorn
Price: $ 775 (PC)
$ 2700 (SPARCstation)
$ 1800 (SPARCstation/educational)
Free educational version
DESIRE (Direct Executing SImulation in REal time) is a completely
interactive system for dynamic-system simulation (up to 6,000
differential equations plus up to 20,000 difference equations in scalar
or matrix form; 13 integration rules) for control, aerospace, and
chemical engineering, physiological modeling, and ecology. Easy
programming of multirun studies (statistics, optimization). Complex
frequency-response plots, fast Fourier transforms, screen editor,
connection to database program. DESIRE/NEUNET adds interactive neural-network simulation (to 20,000 interconnections) and fuzzy logic. Simulates complete dynamic systems controlled by neural networks and/or fuzzy logic. Users can develop their own neural networks using an easily readable matrix notation, as in:
VECTOR layer2= tanh(W * layer1 + bias)Over 200 examples include:
SCREEN-EDITED PROGRAMS RUN IMMEDIATELY AT HIGH SPEED
Package includes 2 textbooks by G.A. Korn: "Neural Networks and Fuzzy-logic Control on Personal Computers and Workstations" (MIT Press, 1995), and "Interactive Dynamic-system Simulatiuon under Windows 95 and NT" (Gordon and Breach, 1998). Please see our Web site for complete tables of contents of books, screen shots, list of users: http://members.aol.com/gatmkorn
Complete educational versions of DESIRE/NEUNET for Windows 95 and NT can now be downloaded FREE as a .zip file which you un-zip to get an automatic INSTALLSHIELD installation program. The educational version is identical to our full industrial version except for smaller data areas (6 instead of 6000 differential equations, smaller neural networks). It will run most examples from both textbooks.
Product: Viscovery SOMine
Company: eudaptics software gmbh
Address: Helferstorferstr. 5/8
A-1010 Vienna
AUSTRIA
Phone: (+43 1) 532 05 70
Fax: (+43 1) 532 05 70 -21
e-mail: office@eudaptics.co.at
URL: http://www.eudaptics.co.at/
Operating System: Windows 95, Windows NT 4.0
Prices: $1495 (commercial),
$695 (non-commercial, i.e. universities)
Viscovery SOMine is a powerful and easy-to-use tool for exploratory data
analysis and data mining. Employing an enhanced version of Self
Organizing Maps it puts complex data into order based on its similarity.
The resulting map can be used to identify and evaluate the features
hidden in the data. The result is presented in a graphical way which
allows the user to analyze non-linear relationships without requiring
profound statistical knowledge. The system further supports full pre-
and postprocessing, cluster search, association/recall, prediction,
statistics, filtering, and animated system state monitoring. Through
the implementation of techniques such as SOM scaling, the speed in
creating maps is increased compared to the original SOM algorithm. Download a free evaluation copy from http://www.eudaptics.co.at/demo.htm
Product: NeuNet Pro
Company: CorMac Technologies Inc.
Address: 34 North Cumberland Street
Thunder Bay, ON P7A 4L4
Canada
Phone: (807) 345-7114
Fax: (807) 345-7114
Email: sales@cormactech.com
URL: http://www.cormactech.com
NeuNet Pro is a complete neural network development system:
Product: NNetView
Company: Neuronics Inc.
Address: Technoparkstr. 1
CH-8005 Zurich Switzerland
Phone: +41 1 445 16 40
Fax: +41 1 445 16 44
URL: http://www.neuronics.com
Operating systems: Windows 95/98/NT and on MacOS.
Prices: 120 EUR for Simulator
310 EUR for Full version incl. camera- and serial interface
1260 EUR for Class licence
NNetView is a simulator for neural networks that allows you to connect
the network directly to the video camera input as well as the
input/output of the serial port of your PC. In addition, the network can
include a free architecture of 2-dimensional layers with connections in
all directions. The most interesting feature is that you can combine
different standard network types (such as Backpropagation, Hebb,
Reinforcement Learning, Kohonen or Hopfield networks). NNetView allows
to learn images (such as faces or colored objects) online and to make
robots and other machines adaptive.
Product: NN50.DLL Neural Network Software Development Kit (SDK)
Company: RG Software Corporation
Address: 6838 W. Cholla
Peoria, Arizona 85345
Phone: (623) 773-2396
FAX: (623) 334-3421
Email: sales@rgsoftware.com
URL: http://www.rgsoftware.com
The NN50.DLL Neural Network SDK allows you to incorporate a quickprop
neural network in your favorite development environment (VB, FoxPro,
C++, Assembler, Java and just about any other Windows programming
language) with minimal investment and effort. NN50.DLL trains very fast,
saves and loads weights, can be used online, stopped and called during
training and more. NN50's input relevance function is based on
information gathered from
ftp://ftp.sas.com/pub/neural/importance.html.
NN50 is compatible with Windows 95, Windows 98, Windows NT and Windows
2000. Unix and Linux versions are also available. Please see
http://www.rgsoftware.com
for details.
Product: Code Builder - Neural Network Edition
Company: Cobalt A.I. Software
Phone: (623) 487-3813
Email: sales@cobaltai.com
URL: http://www.cobaltai.com
Price: U.S. $59.00
Cobalt A.I. Code Builder - Neural Network Edition is a neural
network source code generator. Design neural networks and generate
efficient object oriented source code for C++, Java or Visual Basic
(VB, Excel, Access, Word). Other languages (FoxPro, C# and VB.Net)
will soon be integrated. Code Builder uses a "Project Wizard" to
analyze data and suggest inputs, then generates source code
accordingly.
Product: NEURO MODEL and GenOpt
Company: ATLAN-tec KG
Address: Hans-Martin Schleyer Strasse 18A
47877
Germany
Phone: +49 2154 92 48 222
FAX: +49 2154 92 48 100
Email: nm-sales@atlan-tec.com
URL: http://www.atlan-tec.com
Neuro Model (NM) is a Windows based ANN Development Package which does
not require any scientific knowledge of ANN. Designed for the process
industry, NM showed its best performance with real world data sets.
Preprocessing of all data sets by a proprietary cluster algorithm
provide reliable and consistant information for training. The internal
combination of different mathematical methods eliminates the problem of
local optima and overfitting. Modelling of dynamic non-linearity with
implemented time behaviour enables the package to predict process
conditions online in complexe enviroments like chemical reactors.
Extensive reports of all net details include information about
training parameters and statistics alerts. Software validation conform
FDA could be done by worldwide co-operation with Pharmaplan (FRESENIUS
AG).
Applications References available for:
------------------------------------------------------------------------Next part is part 7 (of 7). Previous part is part 5.