Skip to Content

The Neuroph Project

Posted in

Neuroph is a lightweight Java framework for developing neural networks. It can be used to create and train common neural network architectures.


It has small number of basic classes that correspond to the basic neural network concepts, so it is very intuitive and easy to learn. If you are a beginner in neural networks, or you just want to try how they work without going into complicated theory and implementation, or you need them for your research project - the Neuroph is a good choice for you.

Find out more about Neuroph at, or contact Zoran Sevarac, the Neuroph founder and developer.


The objective of this project is to create easy to use, flexible and well documented development environment for neural networks . The Neuroph framework provides a set of Java classes which can be used to easily create neural networks in Java code, and also the GUI application to create, train and save neural networks as Java components. Created networks can then be used in Java programs.

Basic Info


Current release: 2.8
Programming language: Java
User Interface: Java Swing, NetBeans Platform
Operating System : OS Independent
Intended Audience : Developers, Science/Research
License: Apache 2 Licence
Topic: Neural networks, Frameworks, Simulations
Official project website: 
SourceForge project page:


  • Supports the following neural network architectures: Adaline, Perceptron, Multi Layer Perceptron with Backpropagation, Hopfield,Kohonen,NFR (Neuro Fuzzy Reasoner), Hebbian network, Maxnet, Competitive network, RBF network
  • Provides nice GUI to create,  train and test neural networks
  • Provides image recognition library with easy to use API
  • Well documented, with intuitive API

Succesfull Applications

Project Members

Zoran Sevarac
Marko Koprivica
Jon Tait
and many other contributors


Neuroph started as a graduate thesis project, after that master theses, and on September 2008. it became open source project on SourceForge. After the initial release,  development continued and several people helped to improve it in many ways. After a few months the version 2 was released,  with many new features, optimized and cleaned code.


The current release is always available for download here



Neuroph on the Web