Martin Reczko’s Topic
Subject: Upgrading the Stuttgart Neural Network Simulator (SNNS)
The Stuttgart Neural Network Simulator (SNNS) is a software simulator for neural networks originally developed at the Institute for Parallel and Distributed High Performance Systems at the University of Stuttgart. The goal of the SNNS project is to create an efficient and flexible simulation environment for research on and application of neural nets. Members of our lab participated in the development of SNNS. Within this thesis some recent algorithmic advances like the rectifier linear unit or dropout learning will be added to the SNNS system and benchmarked in the classic bioinformatics task of protein secondary structure prediction. Basic knowledge of neural networks and C programming is required.