Objective:

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

The course focuses on the current understanding of the fundamental principles of cognition, their computational implementations, and practical applications. The course 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. Computational techniques are given for these mechanisms and abilities. A number of applications are discussed. The goals of the course are: First, to provide a basic mathematical understanding of the working of the mind. Second is to demonstrate practical applications of these mechanisms for pattern recognition, tracking, fusion, search engines, and for integrated systems combining sensor signals and communication data. Thirdly is 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 course, 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 and intelligent signal processing. This course assumes a basic understanding of theory of probability.

Handouts:

Copies of the course outline slides. Text: “Neural Networks and Intellect”, L.Perlovsky, Oxford Univ. Press, 2001

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

Course Outline:

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

1.1.      physics and mathematics of the mind

1.2.      genetic argument for the first principles

1.3.      the nature of understanding

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

1.5.      CC since 1950s

1.6.      CC vs. logic

1.7.      mathematics vs. the mind

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

1.9.      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.      Block-Diagrams

2.5.      Hierarchical structure

2.6.      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.      Humboldt’s inner linguistic form

4.5.      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.      MFT dynamics: elementary thought process

5.6.      consciousness and unconscious

5.7.      understanding

5.8.      models-concept-agents

5.9.      symbols, signs, and semiotics

5.10.    aesthetic emotion and beauty

5.11.    intuition: art, mathematics, physics

5.12.    list of applications

5.13.    future tests of the theory

6. Future directions

6.1.      evolving integrated systems

6.2.      evolution of culture

6.3.      mathematics of differentiation and synthesis

Course Summary and Conclusion

Lecturer’s Biography:

Dr. Leonid Perlovsky is Principal Research Physicist and Technical Advisor at the Air Force Research Laboratory/SNHE. Previously, from 1985 to 1999, he served as Chief Scientist at Nichols Research, a $0.5 B high-tech organization, leading the corporate research in information science, intelligent systems, neural networks, optimization, sensor fusion, and algorithm development. In the past he served as professor at Novosibirsk University and New York University. He participated as a principal in commercial startups developing tools for text understanding, biotechnology, and financial predictions. He published about 50 papers in refereed scientific journals and about 150 papers in conferences, delivered invited keynote plenary talks and authored a book “Neural Networks and Intellect: model-based concepts”, Oxford University Press, 2001. Dr. Perlovsky serves on IEEE Computational Intelligence Technical Committee, Computational Intelligence Society Multimedia Tutorial Committee, Chair IEEE Boston Computational Intelligence Chapter, as Organizing Committee Member for IEEE World Congress on Computation Intelligence, IEEE International Conference on Computational Intelligence Measurement and  General Chair for IEEE KIMAS conference, and as Editor-in-Chief for an Elsevier journal “Physics of Life Reviews”.

Decision (Run/Cancel) Date for  this Courses is Tuesday, November 1, 2005

Course Fee Schedule:

On-line Registration and Payment

On-line registration is closed for this course, but registration is still available on-site.

Copyright © 2004 IEEE Boston Section. All rights reserved.
Maintained by R M Stelting

Updated Thursday June 28, 2007