International Conference
Integration of Knowledge Intensive Multi-Agent Systems
KIMAS '07:
Modeling, EVOLUTION and Engineering

April 29 – May 3, 2007

Waltham, Massachusetts

Tutorial I

Tutorial II

TUTORIAL I

Bio-Inspired and Cognitive Algorithms for Recognition, Data Mining, Tracking, Fusion, Prediction, and Language Understanding

Lecturer: Leonid Perlovsky, Ph.D., Air Force Research Laboratory

Text: Neural Networks and Intellect,  by Leonid Perlovsky, Oxford University Press, 2001

Objective:

This tutorial covers the rapidly evolving fields of Bio-Inspired and Cognitive algorithms.

The tutorial focuses on the current understanding of the fundamental principles of cognition, their computational implementations, and practical applications. The tutorial discusses the mind mechanisms, including concepts, emotions, instincts, behavior, language, cognition, understanding, thinking, intuitions, conscious and unconscious, abilities for formation of symbols and aesthetic feelings. Joint evolution of languages and cognition are discussed along with evolution of cultures. Computational techniques are given for these mechanisms and abilities. A number of applications are discussed.

The goals of the tutorial are:

• to provide a basic mathematical understanding of the working of the mind.

• to demonstrate practical applications of these mechanisms for pattern recognition, tracking, fusion, search engines, and for integrated systems combining sensor signals and communication data.

• to outline future research directions. Historical and current difficulties in developing intelligent systems (IS) and applications will be discussed along with how cognition and new computational techniques overcome these difficulties.

By the end of the tutorial, students will be familiar with several general applications addressed by IS, computational difficulties encountered over fifty years, and basic novel approaches to overcoming these difficulties.

Targeted for:

Individuals interested in the development and application of intelligent systems, intelligent signal processing, working of the mind and cultural evolution.

Handouts: Copies of the course outline slides.

Text: "Neural Networks and Intellect”, L. Perlovsky, Oxford Univ. Press, 2001 (retail price $104.94)

For more information: email Leonid.Perlovsky@hanscom.af.mil

Tutorial Outline:

1.       Cognition – integration of real-time signals and a priori knowledge

1.1.    the nature of understanding

1.2.    combinatorial complexity (CC) – a fundamental problem?

1.3.    CC since 1950s

1.4.    CC vs. logic

1.5.    mathematics vs. the mind

1.6.    structure of the mind: concepts, instincts, emotions, behavior

1.7.    instinct for knowledge and aesthetic emotion

2.       Modeling Field Theory (MFT) of cognition

2.1.    Formulation. Basic two-layer mechanism: data-concepts

2.2.    Instinct for knowledge = maximize similarity

2.3.    Dynamic Logic Algorithm (DLA)

2.4.    Hierarchical structure

2.5.    Applications: data mining, pattern recognition, tracking, fusion

3.       Language - integration of language data and models

3.1.    Language

3.2.    MFT of language

3.3.    Applications: search engines

4.       Integration of cognition and language

4.1.    Language vs. thinking

4.2.    Past: AI and Chomskyan linguistics

4.3.    Integrated models

4.4.    Integrated hierarchies of language and cognition

4.5.    Humboldt’s inner linguistic form

4.6.    Applications: integrated systems

5.       Prolegomena to a theory of the mind

5.1.    why mind and emotions?

5.2.    from Plato to Kant, Jung, and Grossberg

5.3.    MFT vs. Buddhism

5.4.    mind vs. brain

5.5.    consciousness and unconscious

5.6.    understanding

5.7.    models-concepts-agents

5.8.    symbols, signs, and semiotics

5.9.       aesthetic emotion and beauty

5.10.    intuition: art, mathematics, physics

5.11.    list of applications

5.12.    future tests of the theory

6.       Future directions

6.1.    evolving integrated systems

6.2.    evolution of languages and cultures

6.3. role of music in cognition and in evolution of cultures

6.4.    mathematics of differentiation and synthesis

Tutorial Summary and Conclusion

Lecturer's Biography:

Dr. Leonid Perlovsky is Visiting Scholar at Harvard University, Principal Research Physicist and Technical Advisor at the Air Force Research Laboratory, Hanscom AFB. He is Program Manager for DOD Semantic Web program and leads several research projects. Previously, from 1985 to 1999, he served as Chief Scientist at Nichols Research, a $0.5B high-tech DOD contractor leading the corporate research in intelligent systems, neural networks, sensor fusion, and target recognition. He served as professor at Novosibirsk University and New York University, and participated as a principal in commercial startups developing tools for text understanding, biotechnology, and financial predictions. His company predicted the market crash following 9/11 a week before the event, detecting activities of Al Qaeda traders, and later helped SEC looking for these guys. He delivered invited keynote plenary talks and tutorial lectures worldwide, published more then 250 papers, 7 book chapters, and authored a monograph “Neural Networks and Intellect,” Oxford University Press, 2001 (currently in the 3rd printing). Three books are coming in 2007: “The Knowledge Instinct”, Basic Books; “Neurodynamics” with Dr. R. Kozma, Springer; “Sapient Systems”, with Dr. R. Mayorga, Springer. Dr. Perlovsky organizes conferences on Computational Intelligence, Chairs IEEE Boston Computational Intelligence Chapter. He received the IEEE Distinguished Member of Boston Section Award and International Neural Network Society Gabor Award. He serves as Associate Editor for IEEE Transactions on Neural Networks, Editor-at-Large for “Natural Computations” and Editor-in-Chief for “Physics of Life Reviews.”

---

TUTORIAL II

“Cognitive” Memory and its Applications

by Bernard Widrow

Tutorial Overview:

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 key 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 autoassociative 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:

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 Autumn of 1959. Today, this is the world’s most widely used learning algorithm. 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 a member of the AdCom of the IEEE Computational Intelligence 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,” is in preparation.

Updated: February 08, 2007.