Perturbation techniques for on-chip learning with analogue VLSI MLPs

Journal of Circuits, Systems and Computers

Volumn 6, Issue 2, 1996, Pages 93-113

  Cairns, Graham ^a   Tarassenko, Lionel ^a  

^a UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0043032395     PISSN: 02181266     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218126696000108     Document Type: Article

References (19)

1. J. Alspector et al., "A parallel gradient descent method for learning in analog VLSI neural networks", in Advances in Neural Information Processing Systems, eds. S. Hanson, J. Cowan and C. Giles, vol. 5, Morgan Kaufmann, 1993, pp. 836-844.
2. G. Cairns and L. Tarassenko, "Implementation issues for on-chip learning with analogue VLSI MLPs", in Proc. Fourth IEE Int. Conf. on Neural Networks, June 1995.
3. G. Cauwenberghs, "A fast stochastic error-descent algorithm for supervised learning and optimization", in Advances in Neural Information Processing Systems, eds. S. Hanson, J. Cowan and C. Giles, vol. 5, Morgan Kaufmann, 1993, pp. 244-251.
4. A. Dembo and T. Kailath, "Model-free distributed learning", IEEE Trans. Neural Networks 1, 1 (1990) 58-70.
5. B. Flower and M. Jabri, "Summed weight neuron perturbation: An O(N) improvement over weight perturbation", in Advances in Neural Information Processing Systems, vol. 5, Morgan Kaufmann, 1992, pp. 212-219.
6. S. Fredrickson and L. Tarassenko, "Radial basis functions for speaker identification", in Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, 1994, pp. 107-110.
7. R. Frye, E. Reitman, and C. Wong, "Back-propagation learning and nonidealities in analog neural network hardware", IEEE Trans. Neural Networks 2 (1991) 110-117.
8. M. Holler, S. Tam, H. Castro, and R. Benson, "An electrically trainable artificial neural network (ETANN) with 10,240 'floating gate' synapses", in Proc. International Joint Conf. on Neural Networks, vol. 2, 1989, pp. 191-196.
9. P. Hollis, J. Harper, and J. Paulos, "The effects of precision constraints in a back-propagation learning network", Neural Computation 2 (1990) 363-373.
10. M. Jabri and B. Flower, "Weight perturbation: An optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks", Neural Computation 3, 4 (1991) 546-565.
11. O. Landolt et al., "CMOS self-biased Euclidean distance computing circuit with high dynamic range", Electronic Letters 28, 4 (1992).
12. J. Lazzaro et al., "Winner-take-all networks of order N complexity", in Proc. IEEE Conf. on Neural Information Processing Systems, 1988.
13. A. Murray and L. Tarassenko, Analogue Neural VLSI, Chapman and Hall, 1994.
14. D. Rumelhart, G. Hinton, and R. Williams, "Learning internal representations by error propagation", in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, eds. D. Rumelhart and J. McClelland, vol. 1: Foundations, The MIT Press, 1986, pp. 318-362.
15. S. Satyanarayana, Y. Tsividis, and H. Graf, "A reconfigurable VLSI neural network", IEEE J. of Solid-State Circuits 27, 1 (1992) 67-81.
16. L. Tarassenko and S. Roberts, "Supervised and unsupervised learning in radial basis function classifiers", in IEE Proc. on Vision, Image and Signal Processing, vol. 141, 1994, pp. 210-216.
17. L. Tarassenko, J. Tombs, and G. Cairns, "On-chip learning with analogue VLSI neural networks", Int. J. Neural Systems 4, 4 (1993) 419-426.
18. B. Widrow and M. Lehr, "30 years of adaptive neural networks: Perceptron, madaline, and back-propagation", Proc. IEEE 78, 9 (1990) 1415-1442.
19. G. Widrow and M. Hoff, "Adaptive switching circuits", IRE, Western Electronic Show and Convention 4, (1960) 96-104.