Adaptive critic for sigma-pi networks

Neural Networks

Volumn 9, Issue 4, 1996, Pages 603-625

  Neville, Richard Stuart ^a   Stonham, Thomas John ^b  

^a BRUNEL UNIVERSITY   (United Kingdom)

^b NONE

Author keywords

Adaptive critic; Associative reward penalty; Dynamic programming; Multi cube; Reinforcement; Sigma pi

Indexed keywords

BACKPROPAGATION; COMPUTER SIMULATION; DYNAMIC PROGRAMMING; MATHEMATICAL MODELS;

ADAPTIVE CRITIC ELEMENT; ASSOCIATIVE REWARD PENALTY; SIGMA PI NETWORKS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; PRIORITY JOURNAL; REINFORCEMENT;

EID: 0030176168     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(96)00015-9     Document Type: Article

References (52)

1. Aleksander, I. (1989a). Canonical neural nets based on logic nodes. In 1st IEE International Conference on Artificial Neural Networks (pp. 110-114).
2. Aleksander, I. (1989b). The logic of connectionist systems (Chapter 8 pp. 135-155), a probabilistic logic neuron network for associative learning (Chapter 9, pp. 156-171) (see also Chapters 1, 10 and 11). In: I. Aleksander (Ed.), Neural computing architectures: the design of brain-like machines, North Oxford Academic Publishers Ltd.
3. Aleksander, I. (1990). Weightless neural tools: towards cognitive macrostructures. In: CAIP Neural Network Workshop. New Jersey: Rutgers University.
4. Barto, A. (1992). Reinforcement learning and adaptive Critic methods. In Handbook of intelligent control: neural, fuzzy, and adaptive approaches (pp. 469-491). New York: Van Nostrand.
5. Barto, A., & Jordan, M. (1987). Gradient following without back-propagation in layered networks. In Proceedings 1st IEEE Conference on Neural Networks (pp. II.629-II.636).
6. Barto, A., Sutton, R., & Anderson, C. (1983). Neuronlike adaptive elements that can solve difficult learning problems. IEEE Transactions on Systems Man, and Cybernetics, SMC-13(5), 834-846.
7. Bledsoe, W. W., & Browning, I. (1959). Pattern recognition and reading machines. In Proceedings of the Eastern Joint Computer Conference (pp. 225-232).
8. Bledsoe, W. W., & Blisson, C. L. (1962). Improved memory matrices for the n-tuple pattern recognition method. IRE Transactions on Electronic Computers, ED11, 141-415.
9. Clarkson, T., Gorse, D., Taylor, J., & Ng, C. (1992). Learning probabilistic RAM nets using VLSI structures. IEEE Transactions on Computers, 41, 1552-1561.
10. Gorse, D., & Taylor, J. (1990a). Reinforcement training strategies for probabilistic RAMs. In Theoretical aspects of neurocomputing: selected papers from the symposium on neural networks and neurocomputing (pp. 180-184). NEURONET90.
11. Gorse, D., & Taylor, J. (1990b). Training strategies for probabilistic RAMs. In Parallel processing in neural systems and computers (pp. 161-164). Amsterdam: North-Holland.
12. Gorse, D., & Taylor, J. (1991). A continuous input RAM-based stochastic neural model. Neural Networks, 4, 657-665.
13. Gullapalli, V. (1988). A stochastic algorithm for learning real-valued functions via reinforcement feedback. COINS Technical Report Number: 88-91, September 29th. The Department of Computer and Information Sciences (COINS), The University of Massachusetts.
14. Gurney, K. (1989). Learning in nets of structure hypercubes. PhD thesis, Department of Electrical Engineering, Brunel University, Manchester (available as: Technical Memo CN/R/144).
15. Gurney, K. (1992a). Training nets of hardware realisable sigma-pi units. Neural Networks, 5, 289-303.
16. Gurney, K. (1992b). Weighted nodes and RAM-nets: A unified approach. Journal of Intelligent Systems, 2(1-4), 155-185.
17. Gurney, K. (1993). Training nets of stochastic units using system identification. Neural Networks, F3 > 6(1), 133-145.
18. Hinton, G., Sejnowski, T., & Ackley, D. (1984). Boltzmann machines: constraint satisfaction networks that learn. Technical Report CMU-CS-84-119, Carnegie Mellon University, Pittsburgh, PA.
19. Hinton, G., Ackley, D., & Sejnowski, T. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9, 147-169.
20. Hui, T., Bolouri, P., & Gurney, K. (1992a). VLSI implementation of digital neural network with reward-penalty learning. 3rd International Workshop on VLSI for Neural Networks and Artificial Intelligence, Oxford University.
21. Hui, T., Gurney, K., & Bolouri, P. (1992b). A cascadable 2048-neuron VLSI artificial neural network with on-board learning. International Conference on Artificial Neural Networks, Brighton, UK.
22. Kan, W.-K., & Aleksander, I. (1987). A probabilistic logic neuron network for associative learning. Proceedings IEEE International Conference on Neural Networks, San Diego, Volume II, pp. II.541-II.548.
23. Minsky, M. (1961). Steps towards artificial intelligence. IRE, 49, 8-30.
24. Minskey, M., & Papert, S. (1969). Perceptrons: an introduction to computational geometry. Cambridge, MA: The MIT Press.
25. Myers, C. (1989). Output functions for probabilistic logic nodes. 1st IEE International Conference on Artificial Neural Networks.
26. Myers, C. (1990). Learning with delayed reinforcement in an exploratory probabilistic logic neural network. PhD thesis, Imperial College of Science, The University of London, Department of Electrical Engineering.
27. Myers, C. & Aleksander, I. (1988). Learning Algorithms for Probabilistic Neural Nets, 1st International Neural Network Society Annual Meeting, Boston, USA.
28. Neville, R. (1990). Investigate and evaluate the design of probabilistic nodes for boolean n-cube networks. Master's thesis, Department of Electrical Engineering, Brunel University.
29. Neville, R. (1993). Augmentation of sigma-pi structures and learning regimes. PhD thesis, Department of Electrical Engineering, Brunel University, Middlesex.
30. Neville, R., & Stonham, T. (1992). Adaptive reward-penalty for probabilistic logic nodes. International Conference on Artificial Neural Networks, IJCNN-92, Brighton.
31. Neville, R., & Stonham, T. (1993). Adaptive critic for probabilistic logic nets. World Congress on Neural Networks (pp. III.389-III.392), Portland, Oregon.
32. Neville, R., & Stonham, T. (1994a). Adaptive associative reward-penalty algorithms for sigma-pi networks. International Journal of Neural, Parallel and Scientific Computations, June, 2(2), 141-164.
33. Neville, R., & Stonham, T. (1994b). Unbounded reinforcement for the associative reward-penalty algorithm. The World Congress on Neural Networks, WCNN-94 (pp. III.637-III.640), San Diego, CA.
34. Neville, R., & Stonham, T. (1994c). A comparison study of unbounded and real-valued reinforcement associative reward-penalty algorithms. The International Conference on Artificial Neural Networks, ICANN-94 (pp. 651-654), Sorrento, Italy.
35. Neville, R., & Stonham, J. (1995). Generalisation in sigma-pi networks. Connection Science: Journal of Neural Computing, Artificial Intelligence and Cognitive Research, March, 7(i) 29-59.
36. Neville, R., Glover, R. J., & Stonham, J. (1995a). Evaluation of training sigma-pi networks on a massively parallel processor. World Congress on Neural Networks, WCNN-95, Washington, DC (pp. II-484-II-487). 1995, International Nueral Network Society Annual Meeting, Renaissance Hotel Washington, DC July 17-21, Volume II, ISBN 0-8058-2125-2.
37. Neville, R., Glover, R. J., & Stonham, J. (1995b). Evaluation of training & mapping sigma-pi networks to a massively parallel processor. IEEE ICNN'95, International Conference on Neural Networks, Perth, Western Australia, 27 November-1 December.
38. Neville, R., Glover, R. J., & Stonham, J. (1995c). Mapping neural networks to the associative string processor. Department of Electrical Engineering, Brunel University, England, Registered as Technical Memorandum N/R/150 in the Department of Electrical Engineering, Brunel University, Copyright © October 1995.
39. Penny, W., Gurney, K., & Stonham, T. (1990). Reward-penalty training for logical neural networks. In International Conference on Artificial Intelligence, Applications and Neural Networks (pp. 26-29), Zurich.
40. Rumelhart, D., McClelland, J., and the PDP Research Group (1986). Parallel distributed processing. Cambridge, MA: MIT Press.
41. Thorndike, E. (1911). Animal intelligence. Darien, CT: Hafner.
42. Werbos, P. (1989). Back-propagation and neurocontrol: A review and prospectus. IEEE Proceedings of the International Joint Conference on Neural Networks (IJCNN'89) (pp. 1:I.209-I.216), New York.
43. Werbos, P. (1990). Consistency of HDP applied to a simple reinforcement learning problem. Neural Networks, 3, 179-189.
44. Werbos, P. (1992a). Approximate dynamic programming for real-time control and neural modelling. In Handbook of intelligent control: neural, fuzzy and adaptive approaches (pp. 493-525), New York: Van Nostrand.
45. Werbos, P. (1992b). Neurocontrol and supervised learning: An overview and evaluation. In Handbook of intelligent control: neural, fuzzy and adaptive approaches (pp. 65-89), New York: Van Nostrand.
46. Werbos, P. (1992c). Neurocontrol and fuzzy logic: Connections and design. International Journal of Approximate Reasoning, 6, 185-219.
47. Widrow, B., & Hoff, M. (1960). Adaptive switching circuits. 1960 IRE Western Electric Show and Convention Record, Part, 4, 96-104.
48. Wilkie, B. A. (1983). A stand-alone, high resolution, adaptive pattern recognition system. PhD Thesis W499, Department of Electrical Engineering, Brunel University, Middlesex.
49. Williams, R. (1986). Reinforcement learning in connectionist networks: a mathematical analysis. Technical Report ICS Report 8605, Cognitive Science, University of California, San Diego, CA.
50. Williams, R. (1987a). A class of gradient-estimation algorithms for reinforcement learning in neural networks. Proceedings of the International Conference on Neural Networks (Vol. II; pp. II.601-II.608), San Diego, CA.
51. Williams, R. (1987b). Reinforcement-learning connectionist systems. Technical Report NU-CCS-87-3, College of Computer Science, Northeastern University, Boston, MA.
52. Witten, I. H (1977). An adaptive optimal controller for discrete-time Markov environments. Inform. Contr., 34, 286-295.