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.
It was a real GOOD OLD AI day today! Just a couple of hours after Filip has become a BSc, Ana has defended her PhD thesis in a brilliant session, with most positive reactions from the members of the committee. Congratulations, Ana!
We are an internationally recognized network of award-winning researchers, engineers, and students working in the fields of applied artificial intelligence and software engineering, situated at the University of Belgrade.