| 06/02/2020 |
Neuroph 2.98 Released |
|
Neuroph 2.98 is a maintainance release and comes with minor API improvements, cleanup of unstable features and bugfixes.
From this version Neuroph is also available on Maven Central repository.
Read the full announcement here
|
|
| 04/05/2019 |
Neuroph 2.96 |
| The new release of Neuroph v2.96 brings folowing improvements:
Neuroph 2.96 comes with various API improvements, several new features, more examples for standard introductory machine learning tasks, and
start of initial integration of Java Visual Recognition API JSR381.
API improvements are related to normalization methods, data set spliting/sampling, and kfold crossvalidation.
There are also inital implementations of new neural network architectures like ART and LSTM.and HE weight initialisation.
Samples project provides examples of 10 standard machine learning problems in package org.neuroph.samples.standard10ml
which are suitable for teaching neural networks and machine learning basics with Java.
This release also includes initial implementation of some parts of Visual Recognition API, which is being developed as official
Java technology Standard for Visual Recognition tasks within JCP (Java Community Process).
Read the full announcement here
|
| 07/13/2017 |
Neuroph 2.94 |
The new release of Neuroph v2.94 brings Release 2.94 brings folowing improvements:
- 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
|
| 11/16/2015 |
Neuroph 2.92 |
| The new release of Neuroph v2.92 brings brings important bug fixes, new tools for crossvalidation and classifier performance evaluation, and new wizard for Convolutional networks. |
| |
|
| 09/22/2014 |
Neuroph at JavaOne 2014 |
| Neuroph will be presented at two sessions. One related to Internet of Things and Rasperry PI and other about Java FX visualization. |
| |
|
| 09/03/2014 |
Neuroph 2.9 Released |
| The new release of Neuroph v2.9 brings brings some new types of neural networks, image preprocessing tools NeurophStudio, and improved 2D visualization for classification sample in Neuroph Studio. The most important this release brings Convolutional neural networks to Neuroph. There are also some adapters for other machine learning frameworks Weka nad Java ML which provides simple integration API. |
| |
|
| 26/04/2014 |
Neuroph Manifesto |
| We have announced the goals and plans for the future Neuroph development in order to encourage interested parties to get involved, and contribute. |
| |
|
| 15/03/2014 |
New NeurophStudio 2.85 Released |
| The new release of NeurophStudio v2.85 brings some important bug fixes, usability improvements and documentation updates
based on the feedback we got on our forum and bugreports. Thanks for helping us in making Neuroph better! |
| |
|
| 10/02/2013 |
Neuroph won the Duke's Choice Award 2013 |
| The Duke’s Choice Awards recognize and honor extreme innovation in the world of Java technology, and are granted
to the most innovative uses of the Java platform. Because the primary judging criteria is innovation, the awards
put even small developers on an equal footing with multinational giants. The winners are selected by Oracle’s Java technology leadership team.
Read more |
| |
|
| 09/16/2013 |
Java Mind Reader - BCI using Neuroph @ JavaOne 2013 |
| Java Mind Reader session at Java One 2013 explains how to use available Java open source tools for BCI signal processing, visualization, and recognition. It briefly covers steps for BCI development and gives general guidelines on signal recognition, along with a demonstration of how to use the Java neural network framework Neuroph for signal classification. Read more |
| |
|
| 09/11/2013 |
Neuroph 2.8 Released |
| The version 2.8 brings great improvenents in GUI NeurophStudio, handy new features on framework level and support for NeuroSky MindWave BCI Read more |
| |
|
| 01/11/2012 |
Neuroph 2.7 Released |
| The version 2.7 has been released! This release brings great new features: significant performance improvements, bug fixes (OCR finally works and black and white image recognition), new GUI features, API cleanup, and many more! Read more |
| |
|
| 10/3/2012 |
Neuroph Session at JavaOne 2012 |
| Session entitled Building Smart Java Applications with Neural Networks, Using the Neuroph Framework presented at JavaOne 2012 was a great success. Read more |
| |
|
| 09/27/2012 |
New NeurophStudio 2.69 release! |
| We have released the new version of NeurophStudio which has many bug fixes, improvements and visual neural network editor! Get it here |
| |
|
| 09/06/2012 |
Neuroph Plugin for Rapid Miner |
| Team from University of Belgrade has created Neuroph plugin for RapidMiner plugin which has been presented at Rapid Miner Community Meeting and Conference. Read more |
| |
|
| 09/02/2012 |
Neuroph in Amazon Cloud |
| Dattaraj Rao created Neuroph based time series prediction application in Amazon Cloud, as a part of engineering tools site |
| |
|
| 08/15/2012 |
A Lots of Step by Step Neuroph Project Samples Published |
| We've published about 30 sample projects created using Neuroph and datasets from UCI Machine Learning Repository.
Projects include classification, prediction, recognition, controll tasks, sample applications and more. |
| |
|
| 06/24/2012 |
Call For Submission For Best Neuroph Application |
| The Neuroph team is now accepting submissions for best applications developed with Neuroph framework. The author of best application will get opportunity to present application at JavaOne 2012 during the Neuroph session:. Read more |
| |
|
| 06/08/2012 |
Neuroph on JavaOne 2012 |
Neuroph will be presented at this years JavaOne conference at session
Building Smart Java Applications with Neural Networks, Using the Neuroph Framework
Session ID: BOF4227 (Zoran Sevarac and Geertjan Wielenga)
Meet us in San Francicsco If you're coming! |
| |
|
| 01/11/2012 |
Neuroph 2.6 Released |
The version 2.6 has been released! This release brings great new features:
Data normalization, Weights randomization, IO Adapters, Advanced image recognition wizard, Android support for image recognition,
Micro benchmarking framework, Resilient propagation and many more! |
| |
|
| 07/22/2011 |
Neuroph 2.5RC2 Released |
New release for Neuroph Studio and framework are available for download at http://neuroph.sourceforge.net/download.html
New release provides many bugfixes for Neuroph Studio and also for framework. This is now recommended release, and we hope it will solve all issues reported lately. Let us know your experience, and thank you for reporting bugs and helping us in development! |
| |
|
|
| 04/28/2011 |
Neuroph Studio RC1 Released |
New minor release for Neuroph Studio and framework are available for download at http://neuroph.sourceforge.net/download.html
New release provides bugfixes for Neuroph Studio GUI and some handy new features for training and testing networks. There are also some minor changes in the Neuroph framework which is released as 2.5.1. This release is now recommended, and it should solve all reported issues so far. |
| |
|
|
| 03/03/2011 |
Neuroph on Oracle Technology Network |
| The article about recently released Neuroph Studio has been published on Oracle Technology Network. This is great for Neuroph promotion and big step for the project. Read the article at http://www.oracle.com/technetwork/articles/java/nbneural-317387.html |
