Turing's Connectionism: A Modern Perspective
|Author:||Christof Teuscher Portland State University|
|Date:||May 23, 2013|
Alan Turing was born on June 23, 1912, in London. While he is best known for breaking the German Enigma code during World War II, his remarkable theoretical and practical contributions to the development of modern computers as well as biology, artificial intelligence, artificial life, and philosophy, led Time magazine to list him among the 20th century's 100 greatest minds. Turing had a keen interest in "intelligent machinery," the general idea that machines could learn to show intelligent behavior. In a little-known 1948 National Physical Laboratory (NPL) report he proposed a special type of neural network as well as evolutionary search, both of which are widely used today. In this talk I will introduce Turing's original neural networks, extensions to them, and then relate the work to contemporary work on random Boolean networks, nano- and molecular electronics, and computability theory. I will also present recent results on robustness, adaptation, and task-solving in such networks.
Christof Teuscher is an assistant professor in the Department of Electrical and Computer Engineering (ECE) with joint appointments in the Department of Computer Science and the Systems Science Graduate Program. He also holds an Adjunct Assistant Professor appointment in Computer Science at the University of New Mexico (UNM). Dr. Teuscher obtained his M.Sc. and Ph.D. degree in computer science from the Swiss Federal Institute of Technology in Lausanne (EPFL) in 2000 and 2004 respectively. In 2004 he became a postdoctoral researcher at the University of California, San Diego (UCSD), in 2005 a distinguished Director's Postdoctoral Fellow at Los Alamos National Laboratory, and in 2007 a Technical Staff Member. His main research focuses on emerging computing architectures and paradigms. For more information visit: http://www.teuscher-lab.com/christof.