News

We are glad to announce that today our member Ivan Dimitrijevic has successfully defended his MSc thesis, "Development of AJAX Web Applications Using the WAD framework". Congratulations, Ivan!

Synesketch, a project by Uros Krcadinac, won the iDMAa Award!

Synesketch was selected for the SIAT's Graduate Student Showcase at the International Digital Media and Arts Association (iDMAa) Conference held at the Emily Carr University of Art and Design, Vancouver, BC, Canada, November 4-6. Eventually, SIAT's Student Showcase won the First Prize among all schools presented at the conference!

Congrats to Uros for this well recognized international award!

Neuroph will be presented at two sessions at JavaOne 2010 conference, the worlds biggest and most influential conference about Java technologies:

Friends of the NetBeans Platform, Tuesday, 09.21.10. at  11:30AM
On this discussion panel we'll present new Neuroph IDE based on NetBeans Platform

BOF: Patterns for Modularity,  Jaroslav Tulach, Zoran Sevarac, Anton Epple, Tuesday, 09.21.10. at  6:00PM
On this session we'll share our experience about porting Neuroph GUI to NetBeans Platform, and creating modular application.

Report and full videos are available here

Two major open source neural network projects for Java platform Encog and Neuroph announced collaboration on development of advanced Java neural network technology. The basic idea for collaboration is to provide the best of both worlds: Encog’s speed (support for multicore and GPU) and Neuroph’s easy to use neuron-based interface on top, for advanced neural network research. This will be accomplished by creating high performance Encog kernel which will also be used by Neuroph. Read the full story here and more about the development plans here

We’ve published an article with Neuroph performance analysis  and released the development version of Neuroph 2.5a which contains backpropagation implementation optimized for high performance.  Along with this we’ve included benchmarking code contributed by tahere as separate NetBeans project. We also announced development plans to improve Neuroph performance and we expect to get feedback from our community and contibutors. We allready managed to improve performance significantly, but we’re going to try some more in order to be competitive with other frameworks. Also we have some results that may show that recent benchmarking might be misleading, but we need some more testing to do.