A pulse-based reinforcement algorithm for learning continuous functions

Neurocomputing

Volumn 14, Issue 4, 1997, Pages 319-344

  Gorse, D ^a   Romano Critchley, D A ^a   Taylor, J G ^b  

^a UNIVERSITY COLLEGE LONDON   (United Kingdom)

^b KING'S COLLEGE LONDON   (United Kingdom)

Author keywords

continuous output reinforcement; pRAM; pulse coding; stochastic computing

Indexed keywords

FUNCTIONS; MATHEMATICAL MODELS; NEURAL NETWORKS; RANDOM ACCESS STORAGE; RANDOM PROCESSES;

CONTINUOUS FUNCTIONS; PROBABILISTIC RANDOM ACCESS MEMORY (PRAM) MODEL; PULSE BASED REINFORCEMENT ALGORITHM; SPIKE BASED REINFORCEMENT LEARNING;

LEARNING ALGORITHMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL;

EID: 0031579674     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(96)00034-3     Document Type: Article

References (31)

1. [1] I.W. Aleksander, W.V. Thomas and P.A. Bowden, WISARD: A radical step forward in pattern recognition, Sensor Review (July 1984) 120-124.
2. [2] I. Aleksander, The logic of connectionist systems, in: I. Aleksander (ed.), Neural Computing Architectures (MIT Press, Cambridge MA, 1989) 133-155.
3. [3] I. Aleksander and H.B. Morton, An overview of weightless neural nets, Proceedings of IJCNN '90 Washington DC Vol. II (1990) 499-502.
4. [4] A.R. Barton, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Transactions on Information Theory 39 (1993) 930-945.
5. [5] A.G. Barto, R.S. Sutton and C.W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems, IEEE Trans. Syst. Man and Cyb. 13 (1983) 834-846.
6. [6] A.G. Barto, Learning by statistical cooperation of self-interested neuron-like computing elements, Human Neurobiol. 4 (1985) 229-256.
7. [7] R.M. Burton and G.J. Mpitsos, Event-dependent control of noise enhances learning in neural networks, Neural Networks 5 (1992) 627-637.
8. [8] T.G. Clarkson, D. Gorse, Y. Guan and J.G. Taylor, Applications of the pRAM, Proceedings of IJCNN '91 Singapore (1991) 2618-2623.
9. [9] T.G. Clarkson, C.K. Ng, D. Gorse and J.G. Taylor, A serial-update VLSI architecture for the learning probabilistic neuron, Proceedings oflCANN '91 (1991) 1573-1576.
10. [10] T.G. Clarkson, C.K. Ng, D. Gorse and J.G. Taylor, Learning probabilistic RAM nets using VLSI structures, IEEE Transactions on Computers 41(12) (1992) 1552-1561.
11. [11] T.G. Clarkson, Y. Guan, J.G. Taylor and D. Gorse, Generalization in probabilistic RAM nets, IEEE Transactions on Neural Networks 4(2) (1993) 360-363.
12. [12] R.P. Feinerman and D.J. Newman, Polynomial Approximation (Williams and Wilkins Co., 1974).
13. [13] B.R. Gaines, Stochastic computing systems, Advances in Information Systems Science 2 (1969) 37-172.
14. [14] D. Gorse and J.G. Taylor, An analysis of noisy RAM and neural nets, Physica D-34 (1989) 90-114;
15. [15] T.G. Clarkson, D. Gorse and J.G. Taylor, From wetware to hardware: Reverse engineering using probabilistic RAMs, Journal of Intelligent Systems 2 (1992) 11-30.
16. [16] D. Gorse and J.G. Taylor, Universal associative stochastic leanring automata, Neural Network World 1 (1991) 193-202.
17. [17] D. Gorse, J.G. Taylor and T.G. Clarkson, Learning real-valued functions using a stochastic reinforcement algorithm, Proceedings of IJCNN '93 Portland OR Vol. III (1993) 301-304.
18. [18] D. Gorse, J.G. Taylor and T.G. Clarkson, A pulse-based reinforcement algorithm for learning continuous functions, Proceedings of WCNN '94 Vol. II (1994) 73-78.
19. [19] C. de Groot and D. Wurtz, Analysis of univariate time series with connectionist nets: A case study of two classical examples, Neural Networks for Statistical and Economic Data (1990_.
20. [20] V. Gullapalli, A stochastic reinforcement learning algorithm for learning real-valued functions, Neural Networks 3 (1990) 671-692.
21. [21] K.N. Gurney, Training nets of hardware realizable sigma-pi units, Neural Networks 5 (1992) 289-303.
22. [22] G.E. Hinton and T.J. Sejnowski, Learning and relearning in Boltzmann machines, in: D.E. Rumelhart and J.L. McClelland (eds.), Parallel Distributed Processing Vol. 1 (MIT Press, Cambridge MA, 1986) 282-317.
23. [23] K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks 2 (1989) 359-366.
24. [24] O. Kufudaki and J. Horejs, PAB: Parameters adapting back-propagation, Preptint, Czechoslovak Academy of Sciences and Charles University, Prague, 1991.
25. [25] P. Mazzoni, R.A. Andersen and M.I. Jordan, A more biologically plausible learning rule for neural networks, Proc. Nail. Acad. Sci. USA 88 (1991) 4433-4437.
26. [26] J.M. McInerney, K.G. Haines, S. Biafore and R. Hecht-Nielsen, Error surfaces of multi-layer networks can have local minima, UCSD Technical Report CS89-157, 1989.
27. [27] J. del R. Millán and C. Torras, A reinforcement connectionist approach to robot path finding in non-maze-like environments, Machine Learning 8 (1992) 363-395.
28. [28] A.F. Murray, D. Del Corso and L. Tarassenko, Pulse-stream VLSI neural networks mixing analog and digital techniques, IEEE Trans. on Neural Networks 2 (1991) 193-204.
29. [29] W.D. Penny and T.J. Stonham, On the generalisation ability and storage capacity of logical neural networks, Proceedings of IJCNN '92 Baltimore Vol. III (1992) 845-849.
30. [30] J. Shawe-Taylor, P. Jeavons and M. van Daalen, Probabilistic bit stream neural chip: Theory, Connection Science 3(1991) 317-328.
31. [31] J.G. Taylor, Spontaneous behaviour in neural networks, J. Theor. Biol. 36 (1972) 513-528.