Scilab Home Page | Wiki | Bug Tracker | Forge | Mailing List Archives | Scilab Online Help | File Exchange
ATOMS : Neural Network Module details

Neural Network Module

This is a Scilab Neural Network Module which covers supervised and unsupervised training algorithms
(7728 downloads for this version - 27153 downloads for all versions)
Tan Chin Luh
Yann Debray
Administrator Atoms
Chin Luh Tan
Creation Date
May 29, 2020
Source created on
Scilab 6.1.x
Binaries available on
Scilab 6.0.x:
Windows 64-bit Windows 32-bit Linux 64-bit Linux 32-bit macOS
Scilab 6.1.x:
Windows 64-bit Windows 32-bit Linux 64-bit Linux 32-bit macOS
Install command
--> atomsInstall("neuralnetwork")
            This Neural Network Module is based on the book "Neural Network
Design" book by Martin T. Hagan. 

The module could be used to build following netwroks
1. Perceptron
2. Adaline
3. Multilayer Feedforware Backpropagation Network
   - Gradient Decent
   - Gradient Decent with Adaptive Learning Rate
   - Gradient Decent with Momentum
   - Gradient Decent with Adaptive Learning Rate and Momentum
   - Levenberg–Marquardt
4. Competitive Network
5. Self-Organizing Map
6. LVQ1 Network

New in ver 3.0: 
1. Feed-forward Back-Propagation Network Base on Andrew Ng's Coursera
Deep-Learning Specialization Course.
2. Updated demos
3. Update for Scilab 6.1            
Files (3)
[1.28 MB]
OS-independent binary for Scilab 6.0.x

[1.27 MB]
OS-independent binary for Scilab 6.1.x

[868.98 kB]
Source code archive

News (0)
Comments (1)
Comment from Rudyak Timur -- December 17, 2020, 10:51:39 PM    
Very cool Neural Network Module! As a professional HVAC contractor in Las Vegas i wonder if
i can use such a neural network that will be able to learn about different Air Conditioner
or Furnace damage types by external, visual look of corresponding HVAC units. We provide
reliable AC repair and replacement services:,
as well as annual AC maintenance in Clark County, so this kind of software would be very
helpful for our clients.