This is part 5 (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 software 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 most 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" or "Our innovative product trains bigger nets
faster." 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 spelling and punctuation.
Rochester Connectionist Simulator
A quite versatile simulator program for arbitrary types of neural nets.
Comes with a backprop package and a X11/Sunview interface. Available via
anonymous FTP from ftp.cs.rochester.edu in directory pub/packages/simulator
as the files README
(8 KB), and rcs_v4.2.tar.Z
(2.9 MB)
UCLA-SFINX
ftp retina.cs.ucla.edu [131.179.16.6];
Login name: sfinxftp; Password: joshua;
directory: pub;
files : README; sfinx_v2.0.tar.Z;
Email info request : sfinx@retina.cs.ucla.edu
NeurDS
Neural Design and Simulation System. This is a general purpose tool for
building, running and analysing Neural Network Models in an efficient manner.
NeurDS will compile and run virtually any Neural Network Model using a
consistent user interface that may be either window or "batch" oriented.
HP-UX 8.07 source code is available from http://hpux.u-aizu.ac.jp/hppd/hpux/NeuralNets/NeurDS-3.1/
or http://askdonna.ask.uni-karlsruhe.de/hppd/hpux/NeuralNets/NeurDS-3.1/
PlaNet5.7 (formerly known as SunNet)
A popular connectionist simulator with versions to run under X Windows,
and non-graphics terminals created by Yoshiro Miyata (Chukyo Univ., Japan).
60-page User's Guide in Postscript. Send any questions to miyata@sccs.chukyo-u.ac.jp
Available for anonymous ftp from ftp.ira.uka.de as /pub/neuron/PlaNet5.7.tar.gz
(800 kb)
GENESIS
GENESIS 2.0 (GEneral NEural SImulation System) is a general purpose simulation
platform which was developed to support the simulation of neural systems
ranging from complex models of single neurons to simulations of large networks
made up of more abstract neuronal components. Most current GENESIS applications
involve realistic simulations of biological neural systems. Although the
software can also model more abstract networks, other simulators are more
suitable for backpropagation and similar connectionist modeling. Runs on
most Unix platforms. Graphical front end XODUS. Parallel version for networks
of workstations, symmetric multiprocessors, and MPPs also available. Available
by ftp from ftp://genesis.bbb.caltech.edu/pub/genesis.
Further information via WWW at http://www.bbb.caltech.edu/GENESIS/.
Mactivation
A neural network simulator for the Apple Macintosh. Available for ftp from
ftp.cs.colorado.edu [128.138.243.151] as /pub/cs/misc/Mactivation-3.3.sea.hqx
Cascade Correlation Simulator
A simulator for Scott Fahlman's Cascade Correlation algorithm. Available
for ftp from ftp.cs.cmu.edu in directory /afs/cs/project/connect/code/supported
as the file cascor-v1.2.shar
(223 KB) There is also a version of recurrent cascade correlation in
the same directory in file rcc1.c
(108 KB).
Quickprop
A variation of the back-propagation algorithm developed by Scott Fahlman.
A simulator is available in the same directory as the cascade correlation
simulator above in file nevprop1.16.shar
(137 KB)
(There is also an obsolete simulator called quickprop1.c
(21 KB) in the same directory, but it has been superseeded by NevProp.
See also the description of NevProp below.)
DartNet
DartNet is a Macintosh-based backpropagation simulator, developed at Dartmouth
by Jamshed Bharucha and Sean Nolan as a pedagogical tool. It makes use
of the Mac's graphical interface, and provides a number of tools for building,
editing, training, testing and examining networks. This program is available
by anonymous ftp from ftp.dartmouth.edu as /pub/mac/dartnet.sit.hqx
(124 KB).
SNNS 4.1
"Stuttgarter Neural Network Simulator" from the University of Tuebingen,
Germany (formerly from the University of Stuttgart): a simulator for many
types of nets with X11 interface: Graphical 2D and 3D topology editor/visualizer,
training visualisation, multiple pattern set handling etc.
Currently supports backpropagation (vanilla, online, with momentum term
and flat spot elimination, batch, time delay), counterpropagation, quickprop,
backpercolation 1, generalized radial basis functions (RBF), RProp, ART1,
ART2, ARTMAP, Cascade Correlation, Recurrent Cascade Correlation, Dynamic
LVQ, Backpropagation through time (for recurrent networks), batch backpropagation
through time (for recurrent networks), Quickpropagation through time (for
recurrent networks), Hopfield networks, Jordan and Elman networks, autoassociative
memory, self-organizing maps, time-delay networks (TDNN), RBF_DDA, simulated
annealing, Monte Carlo, Pruned Cascade-Correlation, Optimal Brain Damage,
Optimal Brain Surgeon, Skeletonization, and is user-extendable (user-defined
activation functions, output functions, site functions, learning procedures).
C code generator snns2c.
Works on SunOS, Solaris, IRIX, Ultrix, OSF, AIX, HP/UX, NextStep, Linux,
and Windows 95/NT. Distributed kernel can spread one learning run over
a workstation cluster.
SNNS web page: http://www-ra.informatik.uni-tuebingen.de/SNNS
Ftp server: ftp://ftp.informatik.uni-tuebingen.de/pub/SNNS
Mailing list: http://www-ra.informatik.uni-tuebingen.de/SNNS/about-ml.html
Aspirin/MIGRAINES
Aspirin/MIGRAINES 6.0 consists of a code generator that builds neural network
simulations by reading a network description (written in a language called
"Aspirin") and generates a C simulation. An interface (called "MIGRAINES")
is provided to export data from the neural network to visualization tools.
The system has been ported to a large number of platforms. The goal of
Aspirin is to provide a common extendible front-end language and parser
for different network paradigms. The MIGRAINES interface is a terminal
based interface that allows you to open Unix pipes to data in the neural
network. Users can display the data using either public or commercial graphics/analysis
tools. Example filters are included that convert data exported through
MIGRAINES to formats readable by Gnuplot 3.0, Matlab, Mathematica, and
xgobi.
The software is available from two FTP sites: from CMU's simulator collection
on pt.cs.cmu.edu [128.2.254.155] in /afs/cs/project/connect/code/unsupported/am6.tar.Z
and from UCLA's cognitive science machine ftp.cognet.ucla.edu [128.97.50.19]
in /pub/alexis/am6.tar.Z
(2 MB).
ALN Workbench (a spreadsheet for Windows)
ALNBench is a free spreadsheet program for MS-Windows (NT, 95) that allows
the user to import training and test sets and predict a chosen column of
data from the others in the training set. It is an easy-to-use program
for research, education and evaluation of ALN technology. Anyone who can
use a spreadsheet can quickly understand how to use it. It facilitates
interactive access to the power of the
Dendronic
Learning Engine (DLE), a product in commercial use.
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. It can learn to
approximate any continuous function to arbitrarily high accuracy.
Parameters allow the user to input knowledge about a function to promote
good generalization. In particular, bounds on the weights of the linear
functions can be directly enforced. Some parameters are chosen automatically
in standard mode, and are under user control in expert mode.
The program can be downloaded from http://www.dendronic.com/beta.htm
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)
PDP++
The PDP++ software is a new neural-network simulation system written in
C++. It represents the next generation of the PDP software released with
the McClelland and Rumelhart "Explorations in Parallel Distributed Processing
Handbook", MIT Press, 1987. It is easy enough for novice users, but very
powerful and flexible for research use.
The current version is 1.0, our first non-beta release. It has been
extensively tested and should be completely usable. Works on Unix with
X-Windows.
Features: Full GUI (InterViews), realtime network viewer, data viewer,
extendable object-oriented design, CSS scripting language with source-level
debugger, GUI macro recording.
Algorithms: Feedforward and several recurrent BP, Boltzmann machine,
Hopfield, Mean-field, Interactive activation and competition, continuous
stochastic networks.
The software can be obtained by anonymous ftp from ftp://cnbc.cmu.edu/pub/pdp++/
and from ftp://unix.hensa.ac.uk/mirrors/pdp++/.
For more information, see our WWW page at http://www.cnbc.cmu.edu/PDP++/PDP++.html.
There is a 250 page (printed) manual and an HTML version available
on-line at the above address.
Uts (Xerion, the sequel)
Uts is a portable artificial neural network simulator written on top of
the Tool Control Language (Tcl) and the Tk UI toolkit. As result, the user
interface is readily modifiable and it is possible to simultaneously use
the graphical user interface and visualization tools and use scripts written
in Tcl. Uts itself implements only the connectionist paradigm of linked
units in Tcl and the basic elements of the graphical user interface. To
make a ready-to-use package, there exist modules which use Uts to do back-propagation
(tkbp) and mixed em gaussian optimization (tkmxm). Uts is available in
ftp.cs.toronto.edu in directory /pub/xerion.
Neocognitron simulator
The simulator is written in C and comes with a list of references which
are necessary to read to understand the specifics of the implementation.
The unsupervised version is coded without (!) C-cell inhibition. Available
for anonymous ftp from unix.hensa.ac.uk [129.12.21.7] in /pub/neocognitron.tar.Z
(130 kB).
Multi-Module Neural Computing Environment (MUME)
MUME is a simulation environment for multi-modules neural computing. It
provides an object oriented facility for the simulation and training of
multiple nets with various architectures and learning algorithms. MUME
includes a library of network architectures including feedforward, simple
recurrent, and continuously running recurrent neural networks. Each architecture
is supported by a variety of learning algorithms. MUME can be used for
large scale neural network simulations as it provides support for learning
in multi-net environments. It also provide pre- and post-processing facilities.
The modules are provided in a library. Several "front-ends" or clients
are also available. X-Window support by editor/visualization tool Xmume.
MUME can be used to include non-neural computing modules (decision trees,
...) in applications. MUME is available for educational institutions by
anonymous ftp on mickey.sedal.su.oz.au [129.78.24.170] after signing and
sending a licence: /pub/license.ps
(67 kb).
Contact:
Marwan Jabri, SEDAL, Sydney University Electrical Engineering,
NSW 2006 Australia, marwan@sedal.su.oz.au
LVQ_PAK, SOM_PAK
These are packages for Learning Vector Quantization and Self-Organizing
Maps, respectively. They have been built by the LVQ/SOM Programming Team
of the Helsinki University of Technology, Laboratory of Computer and Information
Science, Rakentajanaukio 2 C, SF-02150 Espoo, FINLAND There are versions
for Unix and MS-DOS available from http://nucleus.hut.fi/nnrc/nnrc-programs.html
Nevada Backpropagation (NevProp)
NevProp, version 3, is a relatively easy-to-use, feedforward backpropagation
multilayer perceptron simulator-that is, statistically speaking, a multivariate
nonlinear regression program. NevProp3 is distributed for free under the
terms of the GNU Public License and can be downloaded from http://www.scsr.nevada.edu/nevprop/
The program is distributed as C source code that should compile and run
on most platforms. In addition, precompiled executables are available for
Macintosh and DOS platforms. Limited support is available from Phil Goodman
(goodman@unr.edu), University of Nevada Center for Biomedical Research.
MAJOR FEATURES OF NevProp3 OPERATION (* indicates feature new in version
3)
-
Character-based interface common to the UNIX, DOS, and Macintosh platforms.
-
Command-line argument format to efficiently initiate NevProp3. For Generalized
Nonlinear Modeling (GNLM) mode, beginners may opt to use an interactive
interface.
-
Option to pre-standardize the training data (z-score or forced range*).
-
Option to pre-impute missing elements in training data (case-wise deletion,
or imputation with mean, median, random selection, or k-nearest neighbor).*
-
Primary error (criterion) measures include mean square error, hyperbolic
tangent error, and log likelihood (cross-entropy), as penalized an unpenalized
values.
-
Secondary measures include ROC-curve area (c-index), thresholded classification,
R-squared and Nagelkerke R-squared. Also reported at intervals are the
weight configuration, and the sum of square weights.
-
Allows simultaneous use of logistic (for dichotomous outputs) and linear
output activation functions (automatically detected to assign activation
and error function).*
-
1-of-N (Softmax)* and M-of-N options for binary classification.
-
Optimization options: flexible learning rate (fixed global adaptive, weight-specific,
quickprop), split learn rate (inversely proportional to number of incoming
connections), stochastic (case-wise updating), sigmoidprime offset (to
prevent locking at logistic tails).
-
Regularization options: fixed weight decay, optional decay on bias weights,
Bayesian hyperpenalty* (partial and full Automatic Relevance Determination-also
used to select important predictors), automated early stopping (full dataset
stopping based on multiple subset cross-validations) by error criterion.
-
Validation options: upload held-out validation test set; select subset
of outputs for joint summary statistics;* select automated bootstrapped
modeling to correct optimistically biased summary statistics (with standard
deviations) without use of hold-out.
-
Saving predictions: for training data and uploaded validation test set,
save file with identifiers, true targets, predictions, and (if bootstrapped
models selected) lower and upper 95% confidence limits* for each prediction.
-
Inference options: determination of the mean predictor effects and level
effects (for multilevel predictor variables); confidence limits within
main model or across bootstrapped models.*
-
ANN-kNN (k-nearest neighbor) emulation mode options: impute missing data
elements and save to new data file; classify test data (with or without
missing elements) using ANN-kNN model trained on data with or without missing
elements (complete ANN-based expectation maximization).*
-
AGE (ANN-Gated Ensemble) options: adaptively weight predictions (any scale
of scores) obtained from multiple (human or computational) "experts"; validate
on new prediction sets; optional internal prior-probability expert.*
Fuzzy ARTmap
This is just a small example program. Available for anonymous ftp from
park.bu.edu [128.176.121.56] ftp://cns-ftp.bu.edu/pub/fuzzy-artmap.tar.Z
(44 kB).
PYGMALION
This is a prototype that stems from an ESPRIT project. It implements back-propagation,
self organising map, and Hopfield nets. Avaliable for ftp from ftp.funet.fi
[128.214.248.6] as /pub/sci/neural/sims/pygmalion.tar.Z
(1534 kb). (Original site is imag.imag.fr: archive/pygmalion/pygmalion.tar.Z).
Basis-of-AI-NN Software
Non-GUI DOS and UNIX source code, DOS binaries and examples are available
in the following different program sets and the backprop package has a
Windows 3.x binary and a Unix/Tcl/Tk version:
[backprop, quickprop, delta-bar-delta, recurrent networks],
[simple clustering, k-nearest neighbor, LVQ1, DSM],
[Hopfield, Boltzman, interactive activation network],
[interactive activation network],
[feedforward counterpropagation],
[ART I],
[a simple BAM] and
[the linear pattern classifier]
For details see: http://www.dontveter.com/nnsoft/nnsoft.html
An improved professional version of backprop is also available; see
Part
6 of the FAQ.
Questions to: Don Tveter, drt@christianliving.net
Matrix Backpropagation
MBP (Matrix Back Propagation) is a very efficient implementation of the
back-propagation algorithm for current-generation workstations. The algorithm
includes a per-epoch adaptive technique for gradient descent. All the computations
are done through matrix multiplications and make use of highly optimized
C code. The goal is to reach almost peak-performances on RISCs with superscalar
capabilities and fast caches. On some machines (and with large networks)
a 30-40x speed-up can be measured with respect to conventional implementations.
The software is available by anonymous ftp from ftp.esng.dibe.unige.it
as /neural/MBP/MBPv1.1.tar.Z
(Unix version), or /neural/MBP/MBPv11.zip
(PC version)., For more information, contact Davide Anguita (anguita@dibe.unige.it).
BIOSIM
BIOSIM is a biologically oriented neural network simulator. Public domain,
runs on Unix (less powerful PC-version is available, too), easy to install,
bilingual (german and english), has a GUI (Graphical User Interface), designed
for research and teaching, provides online help facilities, offers controlling
interfaces, batch version is available, a DEMO is provided.
REQUIREMENTS (Unix version): X11 Rel. 3 and above, Motif Rel 1.0 and
above, 12 MB of physical memory, recommended are 24 MB and more, 20 MB
disc space. REQUIREMENTS (PC version): PC-compatible with MS Windows 3.0
and above, 4 MB of physical memory, recommended are 8 MB and more, 1 MB
disc space.
Four neuron models are implemented in BIOSIM: a simple model only switching
ion channels on and off, the original Hodgkin-Huxley model, the SWIM model
(a modified HH model) and the Golowasch-Buchholz model. Dendrites consist
of a chain of segments without bifurcation. A neural network can be created
by using the interactive network editor which is part of BIOSIM. Parameters
can be changed via context sensitive menus and the results of the simulation
can be visualized in observation windows for neurons and synapses. Stochastic
processes such as noise can be included. In addition, biologically orientied
learning and forgetting processes are modeled, e.g. sensitization, habituation,
conditioning, hebbian learning and competitive learning. Three synaptic
types are predefined (an excitatatory synapse type, an inhibitory synapse
type and an electrical synapse). Additional synaptic types can be created
interactively as desired.
Available for ftp from ftp.uni-kl.de in directory /pub/bio/neurobio:
Get /pub/bio/neurobio/biosim.readme
(2 kb) and /pub/bio/neurobio/biosim.tar.Z
(2.6 MB) for the Unix version or /pub/bio/neurobio/biosimpc.readme
(2 kb) and /pub/bio/neurobio/biosimpc.zip
(150 kb) for the PC version.
Contact:
Stefan Bergdoll
Department of Software Engineering (ZXA/US)
BASF Inc.
D-67056 Ludwigshafen; Germany
bergdoll@zxa.basf-ag.de phone 0621-60-21372 fax 0621-60-43735
The Brain
The Brain is an advanced neural network simulator for PCs that is simple
enough to be used by non-technical people, yet sophisticated enough for
serious research work. It is based upon the backpropagation learning algorithm.
Three sample networks are included. The documentation included provides
you with an introduction and overview of the concepts and applications
of neural networks as well as outlining the features and capabilities of
The Brain.
The Brain requires 512K memory and MS-DOS or PC-DOS version 3.20 or
later (versions for other OS's and machines are available). A 386 (with
maths coprocessor) or higher is recommended for serious use of The Brain.
Shareware payment required.
Demo version is restricted to number of units the network can handle
due to memory contraints on PC's. Registered version allows use of extra
memory.
External documentation included: 39Kb, 20 Pages.
Source included: No (Source comes with registration).
Available via anonymous ftp from ftp.tu-clausthal.de as /pub/msdos/science/brain12.zip
(78 kb) and from ftp.technion.ac.il as /pub/contrib/dos/brain12.zip
(78 kb)
Contact:
David Perkovic
DP Computing
PO Box 712
Noarlunga Center SA 5168
Australia
Email: dip@mod.dsto.gov.au (preferred) or dpc@mep.com or perkovic@cleese.apana.org.au
FuNeGen 1.0
FuNeGen is a MLP based software program to generate fuzzy rule based classifiers.
A limited version (maximum of 7 inputs and 3 membership functions for each
input) for PCs is available for anonymous ftp from obelix.microelectronic.e-technik.th-darmstadt.de
in directory /pub/neurofuzzy.
For further information see the file read.me.
Contact: Saman K. Halgamuge
NeuDL -- Neural-Network Description Language
NeuDL is a description language for the design, training, and operation
of neural networks. It is currently limited to the backpropagation neural-network
model; however, it offers a great deal of flexibility. For example, the
user can explicitly specify the connections between nodes and can create
or destroy connections dynamically as training progresses. NeuDL is an
interpreted language resembling C or C++. It also has instructions dealing
with training/testing set manipulation as well as neural network operation.
A NeuDL program can be run in interpreted mode or it can be automatically
translated into C++ which can be compiled and then executed. The NeuDL
interpreter is written in C++ and can be easly extended with new instructions.
NeuDL is available from the anonymous ftp site at The University of
Alabama: cs.ua.edu (130.160.44.1) in the file /pub/neudl/NeuDLver021.tar.
The tarred file contains the interpreter source code (in C++) a user manual,
a paper about NeuDL, and about 25 sample NeuDL programs. A document demonstrating
NeuDL's capabilities is also available from the ftp site: /pub/neudl/NeuDL/demo.doc
/pub/neudl/demo.doc.
For more information contact the author: Joey Rogers (jrogers@buster.eng.ua.edu).
NeoC Explorer (Pattern Maker included)
The NeoC software is an implementation of Fukushima's Neocognitron neural
network. Its purpose is to test the model and to facilitate interactivity
for the experiments. Some substantial features: GUI, explorer and tester
operation modes, recognition statistics, performance analysis, elements
displaying, easy net construction. PLUS, a pattern maker utility for testing
ANN: GUI, text file output, transformations. Available for anonymous FTP
from OAK.Oakland.Edu (141.210.10.117) as /SimTel/msdos/neurlnet/neocog10.zip
(193 kB, DOS version)
AINET
AINET is a probabilistic neural network application which runs on Windows
95/NT. It was designed specifically to facilitate the modeling task in
all neural network problems. It is lightning fast and can be used in conjunction
with many different programming languages. It does not require iterative
learning, has no limits in variables (input and output neurons), no limits
in sample size. It is not sensitive toward noise in the data. The database
can be changed dynamically. It provides a way to estimate the rate of error
in your prediction. It has a graphical spreadsheet-like user interface.
The AINET manual (more than 100 pages) is divided into: "User's Guide",
"Basics About Modeling with the AINET", "Examples", "The AINET DLL library"
and "Appendix" where the theoretical background is revealed. You can get
a full working copy from: http://www.ainet-sp.si/
DemoGNG
This simulator is written in Java and should therefore run without compilation
on all platforms where a Java interpreter (or a browser with Java support)
is available. It implements the following algorithms and neural network
models:
-
Hard Competitive Learning (standard algorithm)
-
Neural Gas (Martinetz and Schulten 1991)
-
Competitive Hebbian Learning (Martinetz and Schulten 1991, Martinetz 1993)
-
Neural Gas with Competitive Hebbian Learning (Martinetz and Schulten 1991)
-
Growing Neural Gas (Fritzke 1995)
DemoGNG is distributed under the GNU General Public License. It allows
to experiment with the different methods using various probability distributions.
All model parameters can be set interactively on the graphical user interface.
A teach modus is provided to observe the models in "slow-motion" if so
desired. It is currently not possible to experiment with user-provided
data, so the simulator is useful basically for demonstration and teaching
purposes and as a sample implementation of the above algorithms.
DemoGNG can be accessed most easily at http://www.neuroinformatik.ruhr-uni-bochum.de/
in the file /ini/VDM/research/gsn/DemoGNG/GNG.html
where it is embedded as Java applet into a Web page and is downloaded for
immediate execution when you visit this page. An accompanying paper entitled
"Some competitive learning methods" describes the implemented models in
detail and is available in html at the same server in the directory ini/VDM/research/gsn/JavaPaper/.
It is also possible to download the complete source code and a Postscript
version of the paper via anonymous ftp from ftp.neuroinformatik.ruhr-uni-bochum
[134.147.176.16] in directory /pub/software/NN/DemoGNG/. The software is
in the file DemoGNG-1.00.tar.gz
(193 KB) and the paper in the file sclm.ps.gz
(89 KB). There is also a README
file (9 KB). Please send any comments and questions to demogng@neuroinformatik.ruhr-uni-bochum.de
which will reach Hartmut Loos who has written DemoGNG as well as Bernd
Fritzke, the author of the accompanying paper.
PMNEURO 1.0a
PMNEURO 1.0a is available at:
ftp://ftp.uni-stuttgart.de/pub/systems/os2/misc/pmneuro.zip
PMNEURO 1.0a creates neuronal networks (backpropagation); propagation
results can be used as new training input for creating new networks and
following propagation trials.
nn/xnn
Name: nn/xnn
Company: Neureka ANS
Address: Klaus Hansens vei 31B
5037 Solheimsviken
NORWAY
Phone: +47 55 20 15 48
Email: neureka@bgif.no
URL: http://www.bgif.no/neureka/
Operating systems:
nn: UNIX or MS-DOS,
xnn: UNIX/X-windows, UNIX flavours: OSF1, Solaris, AIX, IRIX, Linux (1.2.13)
System requirements: Min. 20 Mb HD + 4 Mb RAM available. If only the
nn/netpack part is used (i.e. not the GUI), much
less is needed.
Approx. price: Free for 30 days after installation, fully functional
After 30 days: USD 250,-
35% educational discount.
A comprehensive shareware system for developing and simulating artificial
neural networks. You can download the software from the URL given above.
nn is a high-level neural network specification language. The current
version is best suited for feed-forward nets, but recurrent models can
and have been implemented as well. The nn compiler can generate C code
or executable programs, with a powerful command line interface, but everything
may also be controlled via the graphical interface (xnn). It is possible
for the user to write C routines that can be called from inside the nn
specification, and to use the nn specification as a function that is called
from a C program. These features makes nn well suited for application development.
Please note that no programming is necessary in order to use the network
models that come with the system (netpack).
xnn is a graphical front end to networks generated by the nn compiler,
and to the compiler itself. The xnn graphical interface is intuitive and
easy to use for beginners, yet powerful, with many possibilities for visualizing
network data. Data may be visualized during training, testing or 'off-line'.
netpack: A number of networks have already been implemented in nn and
can be used directly: MAdaline, ART1, Backpropagation, Counterpropagation,
Elman, GRNN, Hopfield, Jordan, LVQ, Perceptron, RBFNN, SOFM (Kohonen).
Several others are currently being developed.
The pattern files used by the networks, have a simple and flexible format,
and can easily be generated from other kinds of data. The data file generated
by the network, can be saved in ASCII or binary format. Functions for converting
and pre-processing data are available.
NNDT
NNDT
Neural Network Development Tool
Evaluation version 1.4
Bjvrn Saxen
1995
http://www.abo.fi/~bjsaxen/nndt.html
ftp://ftp.abo.fi/pub/vt/bjs/
The NNDT software is as a tool for neural network training. The user
interface is developed with MS Visual Basic 3.0 professional edition. DLL
routines (written in C) are used for most of the mathematics. The program
can be run on a personal computer with MS Windows, version 3.1.
Evaluation version
This evaluation version of NNDT may be used free of charge for personal
and educational use. The software certainly contains limitations and bugs,
but is still a working version which has been developed for over one year.
Comments, bug reports and suggestions for improvements can be sent to:
bjorn.saxen@abo.fi
or
Bjorn Saxen
Heat Engineering Laboratory
Abo Akademi University
Biskopsgatan 8
SF-20500 Abo
Finland
Remember, this program comes free but with no guarantee!
A user's guide for NNDT is delivered in PostScript format. The document
is split into three parts and compressed into a file called MANUAL.ZIP.
Due to many bitmap figures included, the total size of the uncompressed
files is very large, approx 1.5M.
Features and methods
The network algorithms implemented are of the so called supervised type.
So far, algorithms for multi-layer perceptron (MLP) networks of feed-forward
and recurrent types are included. The MLP networks are trained with the
Levenberg-Marquardt method.
The training requires a set of input signals and corresponding output
signals, stored in a file referred to as pattern file. This is the only
file the user must provide. Optionally, parameters defining the pattern
file columns, network size and network configuration may be stored in a
file referred to as setup file.
NNDT includes a routine for graphical presentation of output signals,
node activations, residuals and weights during run. The interface also
provides facilities for examination of node activations and weights as
well as modification of weights.
A Windows help file is included, help is achieved at any time during
NNDT execution by pressing F1.
Installation
Unzip NNDTxx.ZIP to a separate disk or to a temporary directory e.g. to
c:\tmp. The program is then installed by running SETUP.EXE. See INSTALL.TXT
for more details.
Trajan 2.1 Shareware
Trajan 2.1 Shareware is a Windows-based Neural Network simulation package.
It includes support for the two most popular forms of Neural Network: Multilayer
Perceptrons with Back Propagation and Kohonen networks.
Trajan 2.1 Shareware concentrates on ease-of-use and feedback.
It includes Graphs, Bar Charts and Data Sheets presenting a range of Statistical
feedback in a simple, intuitive form. It also features extensive on-line
Help.
The Registered version of the package can support very large networks
(up to 128 layers with up to 8,192 units each, subject to memory limitations
in the machine), and allows simple Cut and Paste transfer of data to/from
other Windows-packages, such as spreadsheet programs. The Unregistered
version features limited network size and no Clipboard Cut-and-Paste.
There is also a Professional version of Trajan 2.1, which supports
a wider range of network models, training algorithms and other features.
See Trajan Software's Home Page at
http://www.trajan-software.demon.co.uk
for further details, and a free copy of the Shareware version.
Alternatively, email andrew@trajan-software.demon.co.uk
for more details.
Neural Networks at your Fingertips
"Neural Networks at your Fingertips" is a package of ready-to-reuse neural
network simulation source code which was prepared for educational purposes
by Karsten Kutza. The package consists of eight programs, each of which
implements a particular network architecture together with an embedded
example application from a typical application domain.
Supported network architectures are
-
Adaline,
-
Backpropagation,
-
Hopfield Model,
-
Bidirectional Associative Memory,
-
Boltzmann Machine,
-
Counterpropagation,
-
Self-Organizing Map, and
-
Adaptive Resonance Theory.
The applications demonstrate use of the networks in various domains such
as pattern recognition, time-series forecasting, associative memory, optimization,
vision, and control and include e.g. a sunspot prediction, the traveling
salesman problem, and a pole balancer.
The programs are coded in portable, self-contained ANSI C and can be
obtained from the web pages at
http://www.geocities.com/CapeCanaveral/1624.
NNFit
NNFit (Neural Network data Fitting) is a user-friendly software that allows
the development of empirical correlations between input and output data.
Multilayered neural models have been implemented using a quasi-newton method
as learning algorithm. Early stopping method is available and various tables
and figures are provided to evaluate fitting performances of the neural
models. The software is available for most of the Unix platforms with X-Windows
(IBM-AIX, HP-UX, SUN, SGI, DEC, Linux). Informations, manual and executable
codes (english and french versions) are available at http://www.gch.ulaval.ca/~nnfit
Contact: Bernard P.A. Grandjean, department of chemical engineering,
Laval University; Sainte-Foy (Quibec) Canada G1K 7P4;
grandjean@gch.ulaval.ca
Nenet v1.0
Nenet v1.0 is a 32-bit Windows 95 and Windows NT 4.0 application designed
to facilitate the use of a Self-Organizing Map (SOM) algorithm.
The major motivation for Nenet was to create a user-friendly SOM algorithm
tool with good visualization capabilities and with a GUI allowing efficient
control of the SOM parameters. The use scenarios have stemmed from the
user's point of view and a considerable amount of work has been placed
on the ease of use and versatile visualization methods.
With Nenet, all the basic steps in map control can be performed. In
addition, Nenet also includes some more exotic and involved features especially
in the area of visualization.
Features in Nenet version 1.0:
-
Implements the standard Kohonen SOM algorithm
-
Supports 2 common data preprocessing methods
-
5 different visualization methods with rectangular or hexagonal topology
-
Capability to animate both train and test sequences in all visualization
methods
-
Labelling
-
Both neurons and parameter levels can be labelled
-
Provides also autolabelling
-
Neuron values can be inspected easily
-
Arbitrary selection of parameter levels can be visualized with Umatrix
simultaneously
-
Multiple views can be opened on the same map data
-
Maps can be printed
-
Extensive help system provides fast and accurate online help
-
SOM_PAK compatible file formats
-
Easy to install and uninstall
-
Conforms to the common Windows 95 application style - all functionality
in one application
Nenet web site is at: http://www.mbnet.fi/~phodju/nenet/nenet.html
The web site contains further information on Nenet and also the downloadable
Nenet files (3 disks totalling about 3 Megs)
If you have any questions whatsoever, please contact: Nenet-Team@hut.fi
or phassine@cc.hut.fi
Machine Consciousness Toolbox
See listing for
Machine
Consciousness Toolbox in part 6 of the FAQ.
NICO Toolkit (speech recognition)
Name: NICO Artificial Neural Network Toolkit
Author: Nikko Strom
Address: Speech, Music and Hearing, KTH, S-100 44, Stockholm, Sweden
Email: nikko@speech.kth.se
URL: http://www.speech.kth.se/NICO/index.html
Platforms: UNIX, ANSI C; Source code tested on: HPUX, SUN Solaris, Linux
Price: Free
The NICO Toolkit is an artificial neural network toolkit designed and optimized
for automatic speech recognition applications. Networks with both recurrent
connections and time-delay windows are easily constructed. The network
topology is very flexible -- any number of layers is allowed and layers
can be arbitrarily connected. Sparse connectivity between layers can be
specified. Tools for extracting input-features from the speech signal are
included as well as tools for computing target values from several standard
phonetic label-file formats.
Algorithms:
-
Back-propagation through time,
-
Speech feature extraction (Mel cepstrum coefficients, filter-bank)
SOM Toolbox for Matlab 5
SOM Toolbox, a shareware Matlab 5 toolbox for data analysis with self-organizing
maps is available at the URL http://www.cis.hut.fi/projects/somtoolbox/.
If you are interested in practical data analysis and/or self-organizing
maps and have Matlab 5 in your computer, be sure to check this out!
Highlights of the SOM Toolbox include the following:
-
Tools for all the stages of data analysis: besides the basic SOM training
and visualization tools, the package includes also tools for data preprocessing
and model validation and interpretation.
-
Graphical user interface (GUI): the GUI first guides the user through the
initialization and training procedures, and then offers a variety of different
methods to visualize the data on the trained map.
-
Modular programming style: the Toolbox code utilizes Matlab structures,
and the functions are constructed in a modular manner, which makes it convenient
to tailor the code for each user's specific needs.
-
Advanced graphics: building on the Matlab's strong graphics capabilities,
attractive figures can be easily produced.
-
Compatibility with SOM_PAK: import/export functions for SOM_PAK codebook
and data files are included in the package.
-
Component weights and names: the input vector components may be given different
weights according to their relative importance, and the components can
be given names to make the figures easier to read.
-
Batch or sequential training: in data analysis applications, the speed
of training may be considerably improved by using the batch version.
-
Map dimension: maps may be N-dimensional (but visualization is not supported
when N > 2 ).
FastICA package for MATLAB
The FastICA algorithm for independent component analysis.
Independent component analysis, or ICA, is neural network or signal
processing technique that represents a multidimensional random vector as
a linear combination of nongaussian random variables ('independent components')
that are as independent as possible. ICA is a nongaussian version of factor
analysis, and somewhat similar to principal component analysis. ICA has
many applications in data analysis, source separation, and feature extraction.
The FastICA algorithm is a computationally optimized method for performing
the estimation of ICA. It uses a fixed-point iteration scheme that has
been found in independent experiments to be 10-100 times faster than conventional
gradient descent methods for ICA. Another advantage of the FastICA algorithm
is that it can be used to estimate the independent components one-by-one,
as in projection pursuit, which is very practical in exploratory data analysis.
The FastICA package for MATLAB (versions 5 or 4) is freeware package
with a graphical user interface that implements the fixed-point algorithm
for ICA. The package is available on the Web at
http://www.cis.hut.fi/projects/ica/fastica/.
Email contact: Aapo Hyvarinen <Aapo.Hyvarinen@hut.fi>
NEXUS: Large-scale biological simulations
Large-scale biological neural network simulation engine. Includes automated
network construction tool that allows extremely complex networks to be
generated according to user-supplied architectural specifications.
The network engine is an attempt at creating a biological neural network
simulator. It consists of a C++ class, called "network". A network object
houses a set of objects of another C++ class, called "neuron". The neuron
class is a detailed functional simulation of a neuron (i.e. the actual
chemical processes that lead to a biological neuron's behavior are not
modeled explicitly, but the behavior itself is). The simulation of the
neuron is handled entirely by the neuron class. The network class coordinates
the functioning of the neurons that make up the neural network, as well
as providing addressing services that allow the neurons to interact. It
is also responsible for facilitating the interface of the neural network
it houses onto any existing software into which the neural network is to
be integrated.
Since a simulated neural network consisting of a large number of heavily
interconnected neurons is extremely difficult to generate manually, NEXUS
was developed. To create a network with NEXUS, one need only describe the
network in general terms, in terms of groups of sets of specifically arranged
neurons, and how the groups interface onto each other and onto themselves.
This information constitutes a network architecture descriptor. A network
architecture descriptor is read by NEXUS, and NEXUS uses the information
to generate a network, building all the neurons and connecting them together
appropriately. This system is analogous to nature's brain construction
system. For example, human brains, in general, are very similar. The basic
design is stored in human DNA. Since it is certainly not possible to record
information about each neuron and its connections, DNA must instead contain
(in some form) what is essentially a set of guidelines, a set of rules
about how the brain is to be laid out. These guidelines are used to build
the brain, just like NEXUS uses the guidelines set out in the network architecture
descriptor to build the simulated neural network.
NEXUS and the network engine have deliberately been engineered to be
highly efficient and very compact. Even so, large, complex networks require
tremendous amounts of memory and processing power.
The network engine:
-
flexible and elegant design; highly customizable simulation parameters;
extremely efficient
-
throughout, nonlinear magnitude decay modeling
-
dendritic tree complexity and network connection density limited only by
the computer hardware
-
simulation of dendritic logic gate behaviors via a sophisticated excitation
thresholding and conduction model
-
detailed simulation of backprop, allowing realistic simulation of associated
memory formation processes
-
simulation of all known postsynaptic memory formation mechanisms (STP,
STD, LTP, LTD)
-
dynamic presynaptic output pattern modeling, including excitation magnitude
dependent output pattern selection
-
simulation of all known presynaptic activity-based output modifiers (PPF,
PTP, depression)
NEXUS:
-
allows networks to be designed concisely and as precisely as is necessary
-
makes massively complex large-scale neural network design and construction
possible
-
allows existing networks to be augmented without disturbing existing network
structure
-
UNIX and Win32 compatible
URL: http://www.sfu.ca/~loryan/neural.html
Email: Lawrence O. Ryan <loryan@sfu.ca>
Netlab: Neural network software for Matlab
http://www.ncrg.aston.ac.uk/netlab/index.html
The Netlab simulation software is designed to provide the central tools
necessary for the simulation of theoretically well founded neural network
algorithms for use in teaching, research and applications development.
It consists of a library of Matlab functions and scripts based on the approach
and techniques described in Neural Networks for Pattern Recognition by
Christopher M. Bishop, (Oxford University Press, 1995). The functions come
with on-line help, and further explanation is available via HTML files.
The Netlab library includes software implementations of a wide range
of data analysis techniques. Netlab works with Matlab version 5.0 and higher.
It is not compatible with earlier versions of Matlab.
NuTank
NuTank stands for NeuralTank. It is educational and entertainment software.
In this program one is given the shell of a 2 dimentional robotic tank.
The tank has various I/O devices like wheels, whiskers, optical sensors,
smell, fuel level, sound and such. These I/O sensors are connected to Neurons.
The player/designer uses more Neurons to interconnect the I/O devices.
One can have any level of complexity desired (memory limited) and do subsumptive
designs. More complex design take slightly more fuel, so life is not free.
All movement costs fuel too. One can also tag neuron connections as "adaptable"
that adapt their weights in acordance with the target neuron. This allows
neurons to learn. The Neuron editor can handle 3 dimention arrays of neurons
as single entities with very flexible interconect patterns.
One can then design a scenario with walls, rocks, lights, fat
(fuel) sources (that can be smelled) and many other such things. Robot
tanks are then introduced into the Scenario and allowed interact or battle
it out. The last one alive wins, or maybe one just watches the motion of
the robots for fun. While the scenario is running it can be stopped, edited,
zoom'd, and can track on any robot.
The entire program is mouse and graphicly based. It uses DOS and
VGA and is written in TurboC++. There will also be the ability to download
designs to another computer and source code will be available for the core
neural simulator. This will allow one to design neural systems and download
them to real robots. The design tools can handle three dimentional networks
so will work with video camera inputs and such.
NuTank source code is free from http://www.xmission.com/~rkeene/NuTankSrc.ZIP
Contact: Richard Keene; Keene Educational Software
Email: rkeene@xmission.com or r.keene@center7.com