Previous: NERV
Up: NEURAL NETWORK SIMULATION TOOLS
Next: Neural Shell
Previous Page: NERV
Next Page: Neural Shell
General Information
- Name
- NETS - A NEURAL NETWORK DEVELOPMENT TOOL
- Source
- COSMIC
The University of Georgia
382 East Broad Street
Athens, GA 30602
U.S.A.
Phone: (706) 542-3265
FAX: (706) 542-4807
Internet: service@cossack.cosmic.uga.edu
- Price
- International Price: Program
40.00
- Target usage
-
Model
- Network Architecture
-
- Paradigms
- NETS uses the back propagation learning method for all of the
networks which it creates. The nodes of a network are usually grouped
together into clumps called layers. Generally, a network will have an
input layer through which the various environment stimuli are
presented to the network, and an output layer for determining the
network's response. The number of nodes in these two layers is
usually tied to some features of the problem being solved. Other
layers, which form intermediate stops between the input and output
layers, are called hidden layers. NETS allows the user to customize
the patterns of connections between layers of a network. NETS also
provides features for saving the weight values of a network which
allows for more precise control over the learning process.
- Limitations
- only backpropagation
Implementation
- Display
-
- User Interface
- NETS is an interpreter. The user is presented
with a prompt which is the simulator's way of asking for input. After a command is issued, NETS
will attempt to evaluate the command, which may produce more prompts
requesting specific information or an error if the command is not
understood. The typical process involved when using NETS consists of
translating the problem into a format which uses input/output pairs,
designing a network configuration for the problem, and finally
training the network with input/output pairs until an acceptable error
is reached.
- Execution
-
- Data Format
- files may be stored in binary or
ASCII format
- Evaluation
-
- Performance
-
System Requirements
- Hardware
- IBM PC, Apple Macintosh, VAX, Sun, HP 9000
- Operating System
-
- Display
-
- Language
-
Installation and Documentation
- Installation
-
- Sources available
-
- Implementation language
- C
- Documentation
-
- Support
-
- User Groups
-
Previous: NERV
Up: NEURAL NETWORK SIMULATION TOOLS
Next: Neural Shell
Previous Page: NERV
Next Page: Neural Shell