Hostname: page-component-586b7cd67f-2brh9 Total loading time: 0 Render date: 2024-11-28T15:07:02.785Z Has data issue: false hasContentIssue false
  • English
  • Français

Back to the future: The return of cognitive functionalism

Published online by Cambridge University Press:  10 November 2017

Leyla Roskan Çağlar  and
Stephen José Hanson
Leyla Roskan Çağlar
Affiliation:
Psychology Department, Rutgers University Brain Imaging Center (RUBIC), Rutgers University, Newark, NJ 07102. [email protected]@rubic.rutgers.eduhttps://leylaroksancaglar.github.io/http://nwkpsych.rutgers.edu/~jose/
Stephen José Hanson
Affiliation:
Psychology Department, Rutgers University Brain Imaging Center (RUBIC), Rutgers University, Newark, NJ 07102. [email protected]@rubic.rutgers.eduhttps://leylaroksancaglar.github.io/http://nwkpsych.rutgers.edu/~jose/
Get access Rights & Permissions [Opens in a new window]

Abstract

The claims that learning systems must build causal models and provide explanations of their inferences are not new, and advocate a cognitive functionalism for artificial intelligence. This view conflates the relationships between implicit and explicit knowledge representation. We present recent evidence that neural networks do engage in model building, which is implicit, and cannot be dissociated from the learning process.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 40 , 2017 , e257
Copyright
Copyright © Cambridge University Press 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Block, N. (1978) Troubles with functionalism. Minnesota Studies in the Philosophy of Science 9:261–325.Google Scholar
Caglar, L. R. & Hanson, S. J. (2016) Deep learning and attentional bias in human category learning. Poster presented at the Neural Computation and Psychology Workshop on Contemporary Neural Networks, Philadelphia, PA, August 8–10, 2016.Google Scholar
Cleeremans, A. (1993) Mechanisms of implicit learning: Connectionist models of sequence processing. MIT Press.CrossRefGoogle Scholar
DeJong, G. & Mooney, R. (1986) Explanation-based learning: An alternative view. Machine Learning 1(2):145–76.Google Scholar
Fodor, J. A. (1981) Representations: Philosophical essays on the foundations of cognitive science. MIT Press.Google Scholar
Hanson, S. J., (1995) Some comments and variations on back-propagation. In: The handbook of back-propagation, ed. Chauvin, Y. & Rummelhart, D., pp. 292–323. Erlbaum.Google Scholar
Hanson, S. J. (2002) On the emergence of rules in neural networks. Neural Computation 14(9):2245–68.Google Scholar
Hanson, S. J. & Burr, D. J., (1990) What connectionist models learn: Toward a theory of representation in connectionist networks. Behavioral and Brain Sciences 13:471–518.Google Scholar
Hanson, S. J., Caglar, L. R. & Hanson, C. (under review) The deep history of deep learning.Google Scholar
Hayes, P. J. (1974) Some problems and non-problems in representation theory. In: Proceedings of the 1st summer conference on artificial intelligence and simulation of behaviour, pp. 63–79. IOS Press.Google Scholar
Horgan, T. & Tienson, J., (1996) Connectionism and the philosophy of psychology. MIT Press.Google Scholar
Lenat, D. & Guha, R. V. (1990) Building large. Knowledge based systems: Representation and inference in the Cyc project. Addison-Wesley.Google Scholar
Lenat, D., Miller, G. & Yokoi, T (1995) CYC, WordNet, and EDR: Critiques and responses. Communications of the ACM 38(11):45–48.CrossRefGoogle Scholar
Mazur, J. E. & Hastie, R. (1978) Learning as accumulation: A reexamination of the learning curve. Psychological Bulletin 85:1256–74.Google Scholar
McCarthy, J. (1959) Programs with common sense at the Wayback machine (archived October 4, 2013). In: Proceedings of the Teddington Conference on the Mechanization of Thought Processes, pp. 756–91. AAAI Press.Google Scholar
McCarthy, J. & Hayes, P. J. (1969) Some philosophical problems from the standpoint of artificial intelligence. In: Machine Intelligence 4, ed. Meltzer, B. & Michie, D., pp. 463–502. Edinburgh University Press.Google Scholar
Metcalfe, J., Cottrell, G. W. & Mencl, W. E. (1992) Cognitive binding: A computational-modeling analysis of a distinction between implicit and explicit memory. Journal of Cognitive Neuroscience 4(3):289–98.Google Scholar
Miller, G. A., Beckwith, R., Fellbaum, C., Gross, D. & Miller, K. J. (1990) Introduction to WordNet: An on-line lexical database. International Journal of Lexicography 3(4):235–44.Google Scholar
Newell, A. & Simon, H. (1956) The logic theory machine. A complex information processing system. IRE Transactions on Information Theory 2(3):61–79.Google Scholar
Prasada, S. & Pinker, S. (1993) Generalizations of regular and irregular morphology. Language and Cognitive Processes 8(1):1–56.CrossRefGoogle Scholar
Putnam, H. (1967) Psychophysical predicates. In: Art, mind, and religion, ed. Capitan, W. & Merrill, D.. University of Pittsburgh Press. (Reprinted in 1975 as The nature of mental states, pp. 429–40. Putnam.)Google Scholar
Saxe, A. M., McClelland, J. L. & Ganguli, S. (2013) Dynamics of learning in deep linear neural networks. Presented at the NIPS 2013 Deep Learning Workshop, Lake Tahoe, NV, December 9, 2013.Google Scholar
Saxe, A. M., McClelland, J. L. & Ganguli, S. (2014) Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. Presented at the International Conference on Learning Representations, Banff, Canada, April 14–16, 2014. arXiv preprint 1312.6120. Available at:https://arxiv.org/abs/1312.6120.Google Scholar
Thurstone, L. L. (1919) The learning curve equation. Psychological Monographs 26(3):2–33.Google Scholar