NetMaker

NetMaker is freeware package for building neural networks. It was developed primarily to support particle interaction classification in high energy and neutrino physics experiments at CERN (SMC, COMPASS, ICARUS). It was also my test-bed for experiments with various algorithms (some well known and some of my own ideas). Now it turned into quite a flexible network designer with many possible applications - the idea is to have networks, pre- / post-processing and data sets split into uniformly working, task independent blocks which may form bigger systems. >>

→ neural engine features
→ papers

Current version is: v0.9.1.7

- download, license, installation notes
- sources are on e-mail request
- history of changes

previous versions:

v0.9.1.2
v0.9.1.1
v0.9.0.5
v0.9.0.1

ROOT interface with an example.
(ROOT homepage)

C++ code to run the network in your programs. (works with networks saved with versions up to 0.9.0.1)

Shall you have any questions, comments - e-mail me.

◦ optimized for speed while maintaining huge data sets;
◦ clear visualization of input data and network results:
      ∙ specialized plots - purity-efficiency, background rejection,
      ∙ histograms - with μ and σ of the distribution,
      ∙ scatter plots - with R_xy linear correlation coefficient,
      ∙ error vs training iteration, real-time updated plots;
◦ written in C#;
◦ calculations optimized in C/asm (SSE2/SSE3/SSE4.1 aware).

Manual