Philipp Michel graduated with a BA (Hons) in Computer Science from the University of Cambridge, UK, in June 2003. While at Cambridge, Philipp was a triple fellow of Churchill College and a fellow of the Cambridge University European Trust. He is also a scholar of the ‘Studienstiftung des Deutschen Volkes’ (German National Merit Foundation).
Philipp is currently pursuing research in humanoid robotics at Yale University as a postgraduate fellow during the 2003-2004 academic year. He plans to continue studies in Computer Science during a doctoral program afterwards.
Philipp’s final year undergraduate research project and dissertation entitled ‘Support Vector Machines in Automated Emotion Classification’ resulted in publications presented at the 10th International Conference on Human-Computer Interaction 2003 in Greece and the Fifth International Conference on Multimodal Interfaces 2003 in Canada.
Philipp was born in Germany and grew up in Greece, Germany, and Costa Rica. He is obsessed with water and loves swimming, surfing, and windsurfing.
Project: Visualizing Learning Systems
While machine learning systems such as artificial neural networks have been employed in a wide range of application domains in the past, their dynamics have often evaded traditional methods of analysis. Throughout this project, the author took an NKS-inspired approach of experimentation and graphical exploration towards the analysis of learning methods, with particular emphasis on the visual properties of their basins of attraction. First, a traditional example of the phenomenon of basins of attraction, Newton’s root finding method, was considered. The aim was to seek complex and interesting behavior through directed experiments. Next, attractors in Hopfield neural networks were investigated through visualization. Finally, the same methodology was applied to search for elementary classification behavior in simple NKS-style sequential substitution systems.
Favorite Three-Color Cellular Automaton
Rule Chosen: 6089974404181