Abstract
This plenary keynote paper marks 35-th anniversary of description of the first artificial brain, a neural network which in addition of computing cognitive actions, computes emotive evaluations of the consequence of those actions. It was designed in 1981, as part of an effort within the Adaptive Networks Group of the COINS Department of University of Massachusetts in Amherst to solve the problems of (1) designing a delayed reinforcement learning mechanism for artificial neural networks and (2) designing a self learning system which will learn without external reinforcement of any kind. This paper describes steps which led toward solution of those problems. The proposed artificial brain, named Crossbar Adaptive Array, can be viewed as a model of cognition-emotion interaction in biological brains, and can be used in building brains for cognitive and emotive robotics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Softbank Robotics: Robots. http://www.ald.softbankrobotics.com
Furber, S.: To build a brain. IEEE Spectr. 49(8), 45–49 (2012)
Strickland, E.: A wiring of the brain. IEEE Spectr. 50(5), 12–14 (2013)
Simon, H.: Motivational and emotional controls of cognition. Psychol. Rev. 74, 29–39 (1967)
Bozinovski, S.: Crossbar Adaptive Array. ANW Group, Computer and Information Science Department, University of Massachusetts at Amherst, 25 November 1981
Bozinovski, S.: A self-learning system using secondary reinforcement. In: Abstracts of the Sixth European Meeting on Cybernetics and Systems Research - 1982, Abstract 87. Austrian Society of Cybernetic Studies, Vienna (1982)
Bozinovski, S.: A self-learning system using secondary reinforcement. In: Trappl, R. (ed.) Cybernetics and Systems Research, pp. 397–402. North-Holland, New York (1982)
Bozinovski, S.: Abstract Automata. In: Cupona, G. (ed.) First Seminar on Cybernetics, Mathematical Institute with Numeric Center, Skopje (1968) (in Macedonian)
Bozinovski, S.: Professor Cupona and the first lecture on abstract automata in Macedonia. Math. Maced. 8, 79–94 (2010)
Glushkov, V.: Introduction to Cybernetics. Academy of Sciences of Ukrainian SSR, Kiev (1964). (in Russian)
Glushkov, V.: Introduction to Cybernetics. Belgrade University, Belgrade (1967). (Translated to Serbian)
Kleene, S.: Representation of events in neural nets and abstract automata. In: Shannon, C., McCarthy, J. (eds.) Automata Studies, pp. 3–42. Princeton University Press, Princeton (1956)
Moore, E.: Gedanken-experiments on sequential machines. In: Shannon, C., McCarthy, J. (eds.) Automata Studies, pp. 129–156. Princeton University Press, Princeton (1956)
Arbib, M.A., Kfoury, A.J., Moll, R.N.: A Basis of Theoretical Computer Science. Springer, New York (1981)
Bozinovski, S.: Perceptron problematics: teaching in pattern recognition. Paper for the First-of-May student research competition. University of Zagreb (1970). (in Croatian)
Bozinovski, S.: Introduction to psychocybernetics. Rev. Psychol. 5, 115–128 (1975). Zagreb. (in Croatian)
Bozinovski, S., Fulgosi, A.: The influence of similarity and the transfer of training on the perceptron training. In: Proceedings of Symposium Informatica, 3-12-1-5, Bled (1976). (in Croatian)
Minsky, M., Papert, S.: Perceptrons: an Introduction to Computational Geometry. MIT Press, Cambridge (1969)
Minsky, M.: Computation: Finite and Infinite Machines. Prentice-Hall, Upper Saddle River (1967)
Klopf, H.: Brain functioning and adaptive systems. Air Force Technical Report, AFCRL 72-0164 (1972)
Arbib, M.: Brains, Machines, and Mathematics. McGraw-Hill, New York (1965)
Arbib, M.: Brain, Machine, and Mathematics. Nauka, Moskow (1968). (in Russian)
Arbib, M.: Theories of Abstract Automata. Prentice-Hall, Upper Saddle River (1969)
Mendel, J., McLaren, R.: Reinforcement learning control and pattern recognition systems. In: Mendel, J., Fu, K.-S. (eds.) Learning and Pattern Recognition Systems, pp. 287–318. Academic Press, Gurugram (1970)
Widrow, B., Gupta, N., Maitra, S.: Punish/Reward: learning with a critic in adaptive threshold systems. IEEE Trans. Syst. Man Cybern. 3(5), 455–465 (1973)
Sutton, R., Barto, A.: Toward a modern theory of adaptive networks: expectation and prediction. Psychol. Rev. 88, 135–170 (1981)
Rescorla, R.A., Wagner, A.R.: A theory of Pavlovian conditioning: variations of the effectiveness of reinforcement and non-reinforcement. In: Blake, A., Procasy, C. (eds.) Classical Conditioning II: Current Research and Theory. Appleton-Century-Crofts, New York (1972)
Widrow, B., Hoff, G.: Adaptive switching circuits. IRE WESCON Conv. Rec. pp. 96–104 (1960)
Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative search network: a reinforcement learning associative memory. Biol. Cybern. 40, 201–211 (1981)
Cannon, R.: Dynamics of Physical Systems. McGraw Hill, New York (1967)
Barto, A., Sutton, R., Anderson, C.: Neuronlike elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 13, 834–846 (1983)
Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)
Watkins, C.: Learning from delayed rewards. Ph.D. thesis, Kings College, Cambridge, England (1989)
Keller, F., Shoenfeld, W.: Principles of Psychology. Appleton-Century-Crofts, New York (1950)
Bozinovski, S.: Robotics and Intelligent Manufacturing System. Gocmar Press, New York (1997). (in Macedonian)
Bozinovski, S.: Inverted pendulum learning control. ANW Memo, Computer Science Department, University of Massachusetts, Amherst, 10 December 1981
Rumelhart, D., McClelland, J., The PDP Group: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press (1986)
Watkins, C.: Combining cross-validation and search. In: Bratko, I., Lavrac, N. (eds.) Progress in Machine Learning, Proceedings of the 2nd European Working Session on Learning, pp. 79–87, Sigma (1987)
Barto, A., Sutton, R., Watkins, C.: Learning and sequential decision making. In: Gabriel, M., Moore, J. (eds.) Learning and Computational Neuroscience: Foundations of Adaptive Networks, pp. 539–602. MIT Press, Cambridge (1990)
Barto, A.: Reinforcement learning. In: Omidvar, O., Elliot, D. (eds.) Neural Systems for Control, pp. 7–30. Academic Press, Gurugram (1997)
Bozinovski, S.: Motivation and emotion in anticipatory behavior of consequence driven systems. In: Butz, M., Sigaud, O., Gerard, P. (eds.) Proceedings of the Workshop on Adaptive Behavior in Anticipatory Learning Systems, Edinburg, pp. 100–119 (2002)
Barto, A., Singh, S., Chentanez, N.: Intrinsically motivated learning of hierarchical collections of skills. In: Proceedings of the 3rd International Conference on Developmental Learning (ICDL 2004), LaJolla, CA (2004)
Sutton, R., Barto, A.: Reinforcement Learning. MIT Press, Cambridge (1998)
Acknowledgement
The author was able to study the Glushkov’s book due to 1968 ideas of Gorgi Cupona for development of computer sciences in Macedonia. The author would like to thank Michael Arbib and Nico Spinelli who enabled working with the 1980/81 ANW group. The author would also like to thank Andrew Barto for allowing the author to join the Adaptive Networks Group again in 1995/96.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Bozinovski, S. (2018). Cognitive and Emotive Robotics: Artificial Brain Computing Cognitive Actions and Emotive Evaluations, Since 1981. In: Stojanov, G., Kulakov, A. (eds) ICT Innovations 2016. ICT Innovations 2016. Advances in Intelligent Systems and Computing, vol 665. Springer, Cham. https://doi.org/10.1007/978-3-319-68855-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-68855-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68854-1
Online ISBN: 978-3-319-68855-8
eBook Packages: EngineeringEngineering (R0)