Biologically Plausible Error-Driven Learning Using Local Activation Differences: The Generalized Recirculation Algorithm

Neural Computation

Volumn 8, Issue 5, 1996, Pages 895-938

  O'Reilly, Randall C ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001569746     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.5.895     Document Type: Article

References (55)

1. Ackley, D. H., Hinton, G. E., and Sejnowski, T. J. 1985. A learning algorithm for Boltzmann machines. Cogn. Sci. 9, 147-169.
2. Almeida, L. B. 1987. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In Proceedings of the IEEE First International Conference on Neural Networks San Diego, CA, M. Caudil and C. Butler, eds., pp. 609-618.
3. Artola, A., and Singer, W. 1993. Long-term depression of excitatory synaptic transmission and its relationship to long-term potentiation. Trends Neurosci. 16, 480.
4. Artola, A., Brocher, S., and Singer, W. 1990. Different voltage-dependent thresholds for inducing long-term depression and long-term potentiation in slices of rat visual cortex. Nature (London) 347, 69-72.
5. Bashir, Z., Bortolotto, Z. A., and Davies, C. H. 1993. Induction of LTP in the hippocampus needs synaptic activation of glutamate metabotropic receptors. Nature (London) 363, 347-350.
6. Battiti, T. 1992. First- and second-order methods for learning: Between steepest descent and Newton's method. Neural Comp. 4(2), 141-166.
7. Bear, M. F., and Malenka, R. C. 1994. Synaptic plasticity: LTP and LTD. Curr. Opin. Neurobiol. 4, 389-399.
8. Bienenstock, E. L., Cooper, L. N., and Munro, P. W. 1982. Theory for the development of neuron selectivity: Orientation specificity and binocular interaction in visual cortex. J. Neurosci. 2(2), 32-48.
9. 2+ chelators blocks induction of long-term depression in rat visual cortex. Proc. Natl. Acad. Sci. U.S.A. 89, 123.
10. Collingridge, G. L., and Bliss, T. V. P. 1987. NMDA receptors - their role in long-term potentiation. Trends Neurosci. 10, 288-293.
11. Crick, F. H. C. 1989. The recent excitement about neural networks. Nature (London) 337, 129-132.
12. Crick, F. H. C., and Mitchison, G. 1983. The function of dream sleep. Nature (London) 304, 111-114.
13. Felleman, D. J., and Van Essen, D. C. 1991. Distributed hierarchical processing in the primate cerebral cortex. Cerebral Cortex 1, 1-47.
14. Galland, C. C. 1993. The limitations of deterministic Boltzmann machine learning. Network 4, 355-379.
15. Galland, C. C., and Hinton, G. E. 1990. Discovering high order features with mean field modules. In Advances in Neural Information Processing Systems, 2, D. S. Touretzky, ed., Morgan Kaufmann, San Mateo, CA.
16. Galland, C. C., and Hinton, G. E. 1991. Deterministic Boltzmann learning in networks with asymmetric connectivity. In Connectionist Models: Proceedings of the 1990 Summer School, D. S. Touretzky, J. L. Elman, T. J. Sejnowski, and G. E. Hinton, eds., pp. 3-9. Morgan Kaufmann, San Mateo, CA.
17. Hancock, P. J. B., Smith, L. S., and Phillips, W. A. 1991. A biologically supported error-correcting learning rule. Neural Comp. 3, 201-212.
18. Hillyard, S. A., and Picton, T. W. 1987. Electrophysiology of cognition. In Handbook of Physiology, Section I: Neurophysiology Volume V: Higher Functions of the Brain, F. Plum, ed., pp. 519-584. American Physiological Society.
19. Hinton, G. E. 1986. Learning distributed representations of concepts. Proceedings of the 8th Conference of the Cognitive Science Society, pp. 1-12. Lawrence Erlbaum, Hillsdale, NJ.
20. Hinton, G. E. 1989a. Connectionist learning procedures. Artificial Intelligence 40, 185-234.
21. Hinton, G. E. 1989b. Deterministic Boltzmann learning performs steepest descent in weight-space. Neural Comp. 1, 143-150.
22. Hinton, G. E., and McClelland, J. L. 1988. Learning representations by recirculation. In Neural Information Processing Systems, 1987, D. Z. Anderson, ed., pp. 358-366. American Institute of Physics, New York.
23. Hinton, G. E., and Sejnowski, T. J. 1986. Learning and relearning in Boltzmann machines, Chap. 7. In Parallel Distributed Processing. Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland, and PDP Research Group, eds., pp. 282-317. MIT Press, Cambridge, MA.
24. 2+ is necessary for the induction of LTP and LTD of monosynaptic EPSPs in prefrontal neurons: An in vitro study in the rat. Synapse 10, 173-175.
25. Hopfield, J. J. 1984. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl Acad. Sci. U.S.A. 81, 3088-3092.
26. 2+ entry into hippocampal neurons. Nature (London) 357, 244-246.
27. 2+ channels can transiently potentiate excitatory synaptic transmission in the hippocampus. Neuron 9, 1175-1183.
28. LeCun, Y., and Denker, J. S. 1991. A new learning rule for recurrent networks. Proceedings of the Conference on Neural Networks for Computing, Snowbird, UT.
29. Levitt, J. B., Lewis, D. A., Yoshioka, T., and Lund, J. S. 1993. Topography of pyramidal neuron intrinsic connections in macaque monkey prefrontal cortex (areas 9 & 46). J. Comp. Neurol. 338, 360-376.
30. Linden, D. J. 1994. Long-term synaptic depression in the mammalian brain. Neuron 12, 457-472.
31. Linsker, R. 1992. Local synaptic learning rules suffice to maximize mutual information in a linear network. Neural Comp. 4, 691-702.
32. Lisman, J. 1994. The CaM Kinase II hypothesis for the storage of synaptic memory. Trends Neurosci. 17, 406.
33. Lisman, J. E. 1989. A mechanism for the Hebb and the anti-Hebb processes underlying learning and memory. Proc. Natl Acad. Sci. U.S.A. 86, 9574-9578.
34. Malenka, R. C., and Nicoll, R. A. 1993. NMDA receptor-dependent synaptic plasticity: Multiple forms and mechanisms. Trends Neurosci. 16, 521-527.
35. Malenka, R. C., Lancaster, B., and Zucker, R. S. 1992. Temporal limits on the rise in postsynaptic calcium required for the induction of long-term potentiation. Neuron 9, 121-128.
36. Mazzoni, P., Andersen, R. A., and Jordan, M. I. 1991. A more biologically plausible learning rule for neural networks. Proc. Natl. Acad. Sci. U.S.A. 88, 4433-4437.
37. McClelland, J. L. 1994. The interaction of nature and nurture in development: A parallel distributed processing perspective. In Current Advances in Psychological Science: Ongoing Research, P. Bertelson, P. Eelen, and G. D'Ydewalle, eds., pp. 57-88. Lawrence Erlbaum, Hillsdale, NJ.
38. Movellan, J. R. 1990. Contrastive Hebbian learning in the continuous Hopfield model. In Proceedings of the 1989 Connectionist Models Summer School, D. S. Touretzky, G. E. Hinton, and T. J. Sejnowski, eds., pp. 10-17. Morgan Kaufmann, San Mateo, CA.
39. Mulkey, R. M., and Malenka, R. C. 1992. Mechanisms underlying induction of homosynaptic long-term depression in area CA1 of the hippocampus. Science 9, 967-975.
40. O'Reilly, R. C. 1996. The Leabra model of neural interactions and learning in the neocortex. Ph.D. thesis. Carnegie Mellon University, Pittsburgh, PA.
41. 2+ entry via synaptically activated NMDA receptors in the induction of long-term potentiation. Neuron 11, 817-823.
42. Peterson, C. 1991. Mean field theory neural networks for feature recognition, content addressable memory, and optimization. Connection Sci. 3, 3-33.
43. Peterson, C., and Anderson, J. R. 1987. A mean field theory learning algorithm for neural networks. Complex Syst. 1, 995-1019.
44. Peterson, C., and Hartman, E. 1989. Explorations of the mean field theory learning algorithm. Neural Networks 2, 475-494.
45. Pineda, F. J. 1987a. Generalization of backpropagation to recurrent and higher order neural networks. In Proceedings of IEEE Conference on Neural Information Processing Systems, Denver, CO, D. Z. Anderson, ed., pp. 602-611. IEEE, New York.
46. Pineda, F. J. 1987b. Generalization of backpropagation to recurrent neural networks. Phys. Rev. Lett. 18, 2229-2232.
47. Pineda, F. J. 1988. Dynamics and architecture for neural computation. J. Complexity 4, 216-245.
48. Press, W. H., Flannery, B. P., Teukolsky, S. A., and Vetterling, W. T. 1988. Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, Cambridge.
49. Rumelhart, D. E., Hinton, G. E., and Williams, R. J. 1986a. Learning internal representations by error propagation, Chap. 8. In Parallel Distributed Processing. Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland, and PDP Research Group, eds., pp. 318-362. MIT Press, Cambridge, MA.
50. Rumelhart, D. E., McClelland, J. L., and PDP Research Group, eds. 1986b. Parallel Distributed Processing. Volume 1: Foundations. MIT Press, Cambridge, MA.
51. Schultz, W., Apicella, P., and Ljungberg, T. 1993. Responses of monkey dopamine neurons to reward and conditioned stimuli during successive steps of learning a delayed response task. J. Neurosci. 13, 900-913.
52. Sutton, S., Braren, M., Zubin, J., and John, E. R. 1965. Evoked-potential correlates of stimulus uncertainty. Science 150, 1187-1188.
53. Tesauro, G. 1990. Neural models of classical conditioning: A theoretical viewpoint. In Connectionist Modelling and Brain Function, S. J. Hanson and C. R. Olson, eds., MIT Press, Cambridge, MA.
54. Zipser, D., and Andersen, R. A. 1988. A back propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature (London) 331, 679-684.
55. Zipser, D., and Rumelhart, D. E. 1990. Neurobiologcial significance of new learning models. In Computational Neuroscience, E. Schwartz, ed., pp. 192-200. MIT Press, Cambridge, MA.