NeurApp

NeurApp is an intuitive software for exploring approximation by artificial neural networks. It can be freely downloaded from this site.

Contents:

About the Software
Documentation
Free Download

System Requirements

Documentation
Screenshots
Links

Other Software

NeurApp -
comparison of approximation with the original function.

About the Software

The simple and intuitive software has been created by Igor Grešovnik and Tadej Kodelja. It is aimed at exploring properties and function of modelling by artificial neural networks. The software is based on the Investigative Generic Library (IGLib) and uses the Aforge.Net neural network library. See the User Manual and the Documentation Section for more details.

Documentation

NeurApp User Manual. PDF document containing instructions for installation, running, and using the software, and some background information about the software. Also available as html page and mhtml document.

NeurApp License Agreement. Contains terms of use of the software.

ReadMe file. Contains very basic information about the software.

NeurApp Code Documentation (base index). Code documentation for the software, automatically generated from documentation comments by Doxygen. Only the top-level part of code and the most relevant libraries are documented here. For additional documentation of base libraries, see the IGLib Code documentation.

Free Download

NeurApp can be downloaded here and can be used free of charge by anyone (see the license agreement). The current version is 1.3.

Download NeurApp (click on the link) or 32-bit version for older (32 bit) Windows systems.

Short installation instructions:

Download the compressed archive by clicking on the download link above.
Unpack contents of the archive to an arbitrary directory.
Run the executable from the location where files were unpacked.
That's it. For more information about how to use the application, run it, click on the "About" tab and then on the "Help" button, or read the user manual.

Checksums for NeurApp.zip (27.650.999 bytes):

MD5: 5a5fd69125fd922621685d9320985dc9
SHA-1: d5f736ffa5bd1ec0a5d94335ee87c49a47245d51
SHA-256: 00a72bc3e98c47612f0ee159bb35ab4e9299b665d263b287d8a6d86bd6576642
SHA-512: 90c007147f41ba75dccb12d36271f2e027abd962425f3812f60b18f6b701e0c138ae53b63b9982f1bef4a2e5e55adbebfa012e4ea7ecd7b0f9b219caaf8604bd

Remark: It is always wise to verify the checksums provided by original authors after downloading application files from the internet. This helps prevent downloading modifies files that are infected with viruses and other malware. Please note that even some well established download sites bundle their downloadable software with adware that in some cases turns much more harmful than just causing slight annoyance by showing unwanted advertisement. If the original authors provide checksums for their application files (such that above), check that actual checksums of downloaded software match the provided checksums (there are plenty of simple applications such as HashForm that make this task really simple). It is also recommended to check downloaded files with strong antivirus tools. I use the VirusTotal online service for that, which checks the uploaded files by more than 50 antivirus solutions existent on the market.

System Requirements

The application requires the 64 bit .NET framework (version 4.0 is used in Neurapp 1.3) or its alternative implementation such as Mono. One of these is available for most modern computing platforms and are many times pre-installed with the operating system. If not yet installed, you will have to download and install the .NET framework (for Widows operating systems) or Mono (cross platform) before using the software.
There may be problems with using the software on some older platforms, e.g. Windows XP. For more details, see the System Requirements Section at the IGLib pages. Currently, only the version 1.1 is available for 32-bit systems.

Examples and Screenshots

Approximation of function of 1 variable.

sampled data for approximation of a function of 2
variables

Generating training data by sampling a user defined reference function of two variables.

sampled data for approximation of a function of 2
variables

Neural network - based model of a user defined function of two variables.Original function is shown for comparison, with errors shown in color scale.

detail - comparison of original function and ANN model

detail - comparison of original function and ANN model

Zoomed-in detail of an area with larger approximation errors.

Model with contours.

Plot of approximated data with contours shown.

Fine tuning display options.

There are a number of display options that make inspection of the approximation and its errors really easy and clear. One can individually switch on or off display of training points, grid, surfaces and contours of the original function and its approximation. Transparency of both surfaces can be continuously adjusted. In this figure, both original and approximated surface were drawn relatively opaque, therefore it is immediately clear where approximated function has higher or lower values than the original one. Contours of the original function are displayed, which gives better feeling of 3D shapes.

Links

Other Software

NeurApp is based on Investigative Generic Library (IGLib).

Some publically available software based on this library includes:

HashForm - application for calculation and verification of checksums (MD5, SHA-1, SHA-256, SHA-512) for files and text.
HashShell - a shell application with various cryptography-related functionality (calculation of hash functions / checksums, symmetric and asymmetric encryption, certificate management, etc.).
NeurApp – an educational application for visually exploring features of function approximation with artificial neural networks (ANN). It creates 1D and 2D ANN models of user defined functions and provides visualization capabilities to compare these models with originals. It can be downloaded from Softpedia.
AnnApp – software for exploring multidimensional ANN-based models.
IGShell - a shell application based on IGLib.
Oscillator Modeller – an educational application for playing with nonlinear driven oscillators and their resonance curves.

Previous Versions

This software is available as freeware and is freely available on these pages. Older version can be downloaded via links below. For download and installation instructions, see the Download Section.

Search within this site:

Maintained by Igor Grešovnik

Updated in March 2017