|
| Project Info |
|
 |
|
Download
Latest recommended release 2.98
In case that some of the above links is broken, all released packages are available here
- Latest development sources at GitHub: https://github.com/neuroph
- Maven repository Since version 2.98 Neuroph jars are available from Maven Central
Release 2.98 brings the folowing:
- Neuroph 2.98 is a maintainance release and comes with various API improvements, cleanup of unstable features and bugfixes.
- It continues the integration/support for Java Visual Recognition API JSR381.
- From version 2.98 it is available from Maven central repository.
- For existing Neuroph users who might need more advanced features and professional support we recommend to take a look at Deep Netts Platform
Deep Netts Platform is built on same philosophy as Neuroph to create intuitive easy-to-use neural network/deep learning environment for software developers,
and more advanced features and implementation. The future releases of Neuroph will include Deep Netts community edition, in order to
provide better support for convolutional networks for image recognition.
Requirements
To use Neuroph you need Java 8 or higher
|
 |
Help us improve Neuroph for teaching neural networks
Please fill the quick survey
Register to join the Neuroph community
Fill the registration form Registration is optional, and registered users will have priority in support, feature requests, and will have opportunity to participate in closed and exclusive Neuroph events and activities.
OLDER RELEASES
Older releases are available for download here
2.96
- Neuroph 2.96 comes with various API improvements, several new features, more examples for standard introductory machine learning tasks, and
initial implementation of Java Visual Recognition API JSR381.
- API improvements are related to normalization methods, data set spliting/sampling, HE weight initialisation and kfold crossvalidation.
There are also inital implementations of new neural network architectures like implementation of ART and LSTM.
- Samples project provides package org.neuroph.samples.standard10ml with examples of 10 standard machine learning problems
which are suitable for teaching neural networks and machine learning basics with Java.
- Also there are several contributions in Contrib project related to hyper parameter search and, backpropagation benchmarking,
and cross entropy loss function which are still not fully tested and integrated.
- This release also includes initial implementation of parts of Visual Recognition API, which is being developed as official
Java technology Standard for Visual Recognition tasks within JCP (Java Community Process).
2.94
- Rewrite of all LMS based learning algorithms in order to better reflect the underlying mathematical model
- Multi threaded cross-validation
- Improved Basic Neuron Sample in Neuroph Studio, Jovana Petkovic, University of Belgrade
- Data set visualization and statistics (display histogram with mean, std, min, max, freq for all columns) Aleksandar Arsenovic, University of Belgrade
- Support for loading arff files into Neuroph Studio, Aleksandar Arsenovic, University of Belgrade
- Better JUnit tests (thanks to Tijana Vujacic from University of Belgrade)
- Benchmarking backpropagation algorithms - Mladen Savic, University of Belgrade
- Auto MLP Mtrainer - Milan Brkic, University of Belgrade
- Fixed bugs in image recognition wizard
- Various other bug fixes
2.93b
2.92
2.9
2.8
2.7
2.6
2.5RC2
2.5RC1
2.5. easyNeurons-1.6.zip Old Swing GUI, with support for new framework [32 Mb]
neuroph-2.5b-with-easynurons_nb.zip Complete NetBeans project tree with sources for Neuroph framework and easyNeurons GUI [19 Mb]
2.4. (sample OCR tools and API, stock market prediction sample, learning visualization samples, DynamicBackpropagation, BiasNeuron, min error change stop condition, pause learning feature and more)
2.3.1. (few bugfixes, improved graph view)
2.3. (Image recognition support, code samples, important API changes, improved documentation)
2.2 (improved backpropagation, gui, network error graph, training set imports, new networks and learning rules, help system)
2.1.1_beta (mainly bug fixes for the previous release)
2.1.0_beta (separated library from application, removed deprecated threading control, cleaned compilation warnings, plugins architecture, labels, improved gui)
2.0.0_alpha (added new GUI editor easyNeurons, network architectures and learning rules)
1.0.1_alpha (added serialization support and various optimizations)
1.0.0_alpha and it contains:
- Full Java sources
- API documentation
- Demo application with GUI for creating and training neural networks
- Short introductory tutorial
OTHER
NEAT Support Demo release of NEAT support for Neuroph is available for download here
 |
Softpedia guarantees that Neuroph is 100% Free, which means it does not contain any form of malware, including but not limited to: spyware, viruses, trojans and backdoors. |
|
