Neural networks and artificial intelligence

ABSTRACT

Neural networks have been called “more important than the atomic bomb” and have received a major funding commitment from DARPA. Nevertheless, it is difficult to find even a mention of neural network concepts and applications in many computer science or information systems curricula. In fact, few computer science or information systems faculty are aware of the profound implications of neurocomputing on the future of their field. This paper contends that neural networks must be a significant part of any artificial intelligence course. It illustrates how neural network concepts can be integrated into traditional artificial intelligence course material. Two programming packages for simulating neural networks on personal computers are recommended.

REFERENCES

• 1: Special Issue on Artificial Neural Systems. Computer, March 1988.
• 2: Cowan JD, Sharp DH. Neural Nets and Artificial Intelligence. Daedalus 1988; 117: 85-122.
• 3: Castelaz PF. Application of Neural Network Solution to Battle Management Processing Functions. 55th Military Operations Research Society Symposium, Huntsville AL, May 1987.
• 4: McCuUoch WS, Pitts W. A Logical Calculus of the Ideas Immanent in Nervous Activity. Bull Mathematical Biophysics 1943; 5: 115-133.
• 5: Hebb DO. The Organi~fion of Behavior. New York: John Wiley, 1949.
• 6: Rosenblatt F. The Perceptron, A Probabilistic Model for Information Storage and Organization in the Brain. Psychological Review 1958; 62: 386.
• 7: Rosenblatt F..Prindpl~~ of Nextrodvn~amic~. New York: Spartan, 1962.
• 8: Minsky M, Papert S. Perceptrons: An Introductiont~o Computat.i'onal Geometry. Cambridge MA: MIT Press, 1969.
• 9: Grossberg S. Studies of Mind and Brain. Reidel, 1982.
• 10: Hinton GE. Learning Distributed Presentations of Concepts. Proc Cognitive Science Society, Amherst MA, August 1986.
• 11: T. Kohonen, Self-organization and associative memory: 3rd edition, Springer-Verlag New York, Inc., New York, NY, 1989
• 12: James A. Anderson , Edward Rosenfeld, Neurocomputing: foundations of research, MIT Press, Cambridge, MA, 1988
• 13: Hopfield JJ. Neural Networks and Physical Systems with Emergent Collective Computational Properties. Proc National Academy of Sciences 1982; 79: 2554-2558.
• 14: Hopfield JJ. Neurons With Graded Response Have CoUective Computational Properties Like Those of Two- State Neurons. Proc National Academy of Science 1984; 81: 3088-3092.
• 15: Hopfield JJ, Tank DW. 'Neural' Computation and Constraint Satisfaction Problems and the Traveling Salesman. Biological Cybernetics 1985; 55: 141-146.
• 16: D. E. Rumelhart , G. E. Hinton , R. J. Williams, Learning internal representations by error propagation, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 17: AIP Conference Proceedings 151 on Neural Networks for Computing, March 1987
• 18: Sejnowski TJ, Rosenberg CR. NETralk: A Parallel Network That Learns to Read Aloud. JHU/EECS-86/01, School of Electrical Engineering and Computer Science, Johns Hopkins University, 1986.
• 19: James L. McClelland , David E. Rumelhart, Explorations in parallel distributed processing: a handbook of models, programs, and exercises, MIT Press, Cambridge, MA, 1988
• 20: T. J. Schwartz, Twelve-product wrap-up: neural networks, AI Expert, v.3 n.8, p.73-85, August 1988

INDEX TERMS

Primary Classification:
  K. Computing Milieux
  K.3 COMPUTERS AND EDUCATION
      K.3.2 Computer and Information Science Education
          Subjects: Curriculum

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

General Terms:
Design, Human Factors, Management