2008 Meetings

December 18, 2008: "Advances in Cognitive Memory and its Applications" by Prof. Bernard Widrow, Electrical Engineering, Stanford University

Abstract

Regarding the workings of the human mind, memory and pattern recognition seem to be intertwined. You generally do not have one without the other. Taking inspiration from life experience, a new form of computer memory has been devised. Certain conjectures about human memory are keys to the central idea. The design of a practical and useful "cognitive" memory system is contemplated, a memory system that may also serve as a model for many aspects of human memory. The new memory does not function like a computer memory where specific data is stored in specific numbered registers and retrieval is done by reading the contents of the specified memory register, or done by matching key words as with a document search. Incoming sensory data would be stored at the next available empty memory location, and indeed could be stored redundantly at several empty locations. The stored sensory data would neither have key words nor would it be located in known or specified memory locations. Sensory inputs concerning a single object or subject are stored together as vectors in a single "file folder" or "memory folder". When the contents of the folder are retrieved, sights, sounds, tactile feel, smell, etc., are obtained all at the same time. Sensor fusion is a memory phenomenon. The sensory signals are not fused, but they are simply recorded together in the same folder and retrieved together. Retrieval would be initiated by a prompt signal from a current set of sensory inputs or patterns. A search through the memory would be made to locate stored data that correlates with or relates to the present real-time sensory inputs. The search would be done by a retrieval system that makes use of auto-associative artificial neural networks. Applications of cognitive memory systems have been made to visual aircraft identification, aircraft navigation, and human facial recognition. Other applications to speech recognition and control systems are being explored.

Biography

Prof. Bernard Widrow
Bernard Widrow received the S.B., S.M., and Sc.D. degrees in Electrical Engineering from the Massachusetts Institute of Technology in 1951, 1953, and 1956, respectively. He joined the MIT faculty and taught there from 1956 to 1959. In 1959, he joined the faculty of Stanford University, where he is currently Professor of Electrical Engineering.

He began research on adaptive filters, learning processes, and artificial neural models in 1957. Together with M.E. Hoff, Jr., his first doctoral student at Stanford, he invented the LMS algorithm in the autumn of 1959. Today, this is the most widely used learning algorithm, used in every MODEM in the world. He has continued working on adaptive signal processing, adaptive controls, and neural networks since that time.

Dr. Widrow is a Life Fellow of the IEEE and a Fellow of AAAS. He received the IEEE Centennial Medal in 1984, the IEEE Alexander Graham Bell Medal in 1986, the IEEE Signal Processing Society Medal in 1986, the IEEE Neural Networks Pioneer Medal in 1991, the IEEE Millennium Medal in 2000, and the Benjamin Franklin Medal for Engineering from the Franklin Institute of Philadelphia in 2001. He was inducted into the National Academy of Engineering in 1995 and into the Silicon Valley Engineering Council Hall of Fame in 1999.

Dr. Widrow is a past president and currently a member of the Governing Board of the International Neural Network Society. He is associate editor of several journals and is the author of over 100 technical papers and 18 patents. He is co-author of Adaptive Signal Processing and Adaptive Inverse Control, both Prentice-Hall books. A new book, Quantization Noise, was published by Cambridge University Press in June 2008.


October 24, 2008: "Intelligent Control of Teams of Autonomous Robots" by Dr. Enrique H. Ruspini, UCLA

Abstract

Regulation of the actions of teams of collaborating autonomous robots poses problems that are significantly more complex than those considered when developing controllers for single robots. The multiplicity of team formations and interactions, the requirements imposed by communication needs, and the need to distribute resources and control functions substantially increase the dimensions of state and control spaces and the number of operational constraints that must be considered.

In this talk we will present ongoing research on topics related to the control of motions and actions of teams of interacting autonomous robots. We will start by reviewing basic notions of similarity, utility, and preference underlying similarity-based interpretations of fuzzy logic. On the basis of this conceptual framework we will introduce behavior-based approaches where behaviors are defined in terms of mappings, called desirability functions, that define relative preferences, from the perspective of a single goal or objective, for certain actions as a function of the robot state. We will then review blending mechanisms that gracefully combine multiple purposive and reactive behaviors employing fuzzy-logic techniques.

We will extend these notions to the realm of teams of autonomous robots introducing various approaches to the definition of team behaviors. In particular, we will review approaches for the synthesis of hierarchical controllers based on decomposition of the problem on identification of behaviors at the individual, internal organization, and external action levels. We will also review other experiments in the control of distributed robot teams and sensor networks at SRI such as the Centibots project.

Biography

Dr. Enrique H. Ruspini
Enrique H. Ruspini from the University of California at Los Angeles. Prior to joining SRI, Dr. Ruspini held positions at the University of Buenos Aires, the University of Southern California, UCLA's Brain Research Institute, and Hewlett-Packard Laboratories. Dr. Ruspini is a pioneer in the development of fuzzy-set theory and its applications, having introduced its use to the treatment of numerical classification and clustering problems. He has also made significant contributions to the understanding of the foundations of approximate reasoning. His recent research has focused on intelligent planning and control, information fusion, adaptive sensing systems, qualitative system modeling, and knowledge discovery in databases. Dr. Ruspini, who has recently been awarded the 2009 Fuzzy Systems Pioneer Prize by the IEEE, is a Fellow of the Institute of Electrical and Electronic Engineers, a First Fellow of the International Fuzzy Systems Association, a Fulbright Scholar, and a SRI Institute Fellow. Dr. Ruspini was the General Chairman of the Second IEEE International Conference on Fuzzy Systems (FUZZ-IEEE'93) and of the 1993 IEEE International Conference on Neural Networks (ICNN'93) and the 2001 President of the IEEE Neural Networks Council (now IEEE Computational Intelligence Society). Dr. Ruspini is a member of the Advisory and Editorial Boards of numerous technical journals and the author of over 100 research papers.