sevarac - Slashdot User

Open Source Projects Announced Collaboration-> 0

Submitted by sevarac on Monday July 19 2010, @01:45AM

sevarac writes "Two major open source neural network projects for the Java platform, Encog (http://www.heatonresearch.com/encog) and Neuroph (http://neuroph.sourceforge.net) have announced collaboration on the development of advanced Java neural network technology. The basic idea for collaboration is to provide the best of both worlds: Encogs speed (support for multicore and GPU) and Neurophs easy to use neuron-based interface on top, for advanced neural network research. This will be accomplished by creating a high performance Encog kernel which will also be used by Neuroph."
Link to Original Source

Neuroph 2.4 and NetBeans Platform Porting Plans-> 0

Submitted by sevarac on Friday May 28 2010, @07:38AM

sevarac writes "Java neural network framework Neuroph released version 2.4, which brings important improvements related to learning rules, performance improvements, and new features in GUI and API.
After the release of 2.4, development focus will be on porting all the GUI to the NetBeans Platform in order to provide a state of the art neural network editor."
Link to Original Source

Neuroph 2.4 released-> 0

Submitted by sevarac on Tuesday May 25 2010, @11:53AM

sevarac writes "Open source Java neural network framework has released version 2.4 which brings important improvements over rthe previous releases. The main improvements are related to improving algorithms and performance of learning rules. Also there are new features for OCR, stock market prediction and learning vizualisation. The Neuroph provides tools and Java library which make the neural networks available for Java developers 'out of the box', which makes this framework popular in Java community.
This release has changed the licensing from LGPL3 to Apache 2 after the recent initative to integrate Neuroph with Mahout, the Apache machine learning library.
Also there is a project proposal accepted at Google Summer of Code 2010 to make Neuroph run on Hadoop the Apache implementation of Map Reduce, distributed computing framework. The further develoment will include porting Neuroph GUI editor for neural networks to NetBeans Platform in cooperation with Netbeans team, in order to provide state of the art neural network tools."
Link to Original Source

Comment: Re:This wont work... (Score 1) 98

by sevarac on Tuesday October 13 2009, @01:58PM (#29735205) Attached to: Image Recognition Neural Networks, Open Sourced

1. What if you want to classify pictures that have different sizes (not too uncommon)? Wont work because you first have to set a fixed number of neurons in your first layer.

All images are scaled to the same dimensions determined by the sample resolution settings.

2. What about different locations of the same object?

This problem is not adresed here. Suggested approach can be used on whole images or specific known image locations.

Comment: Re:!Open Sourced (Score 1) 98

by sevarac on Tuesday October 13 2009, @01:33PM (#29734925) Attached to: Image Recognition Neural Networks, Open Sourced

Hi, you're right when you say the Neuroph has always been open source, but the image recognition used by http://dota-autoscript.com/ has not been open source. With this release of Neuroph we added the image recognition support based on ideas and original code from http://dota-autoscript.com./

Image Recognition Neural Networks-> 0

Submitted by sevarac on Sunday October 11 2009, @08:40PM

sevarac writes "The latest release of Java Neural Network Framework Neuroph v2.3 comes with ready-to-use image recognition support. It provides GUI tool for training multi layer perceptrons for image recognition, and easy to use API to deploy these neural networks in end-user applications. This image recognition approach has been successfully used by DotA AutoScript tool, and now it is released as open source. With this Java library basic image recognition can be performed in just few lines of code. The developers have published howto article and online demo which can be used to train image recognition neural networks online."
Link to Original Source

Java Program Uses Neural Networks To Monitor Games 100

Posted by Soulskill on Thursday May 14 2009, @01:13AM
from the automating-the-automation dept.

tr0p writes "Java developers have used the open source Neuroph neural network framework to monitor video game players while they play and then provide helpful situational awareness, such as audio queues when a power-up is ready or on-the-fly macros for combo attacks. The developers have published an article describing many of the technical details of their implementation. 'There are two different types of neural networks used by DotA AutoScript. The first type is a simple binary image classifier. It uses Neuroph's "Multi-Layer Perceptron" class to model a neural network with an input neurons layer, one hidden neurons layer, and an output neurons layer. Exposing an image to the input layer neurons causes the output layer neurons to produce the probability of a match for each of the images it has been trained to identify; one trained image per output neuron.'"