publication . Preprint . 2010

Delta Learning Rule for the Active Sites Model

Lingashetty, Krishna Chaithanya;
Open Access English
  • Published: 02 Jul 2010
Abstract
This paper reports the results on methods of comparing the memory retrieval capacity of the Hebbian neural network which implements the B-Matrix approach, by using the Widrow-Hoff rule of learning. We then, extend the recently proposed Active Sites model by developing a delta rule to increase memory capacity. Also, this paper extends the binary neural network to a multi-level (non-binary) neural network.
Subjects
arXiv: Quantitative Biology::Neurons and CognitionComputer Science::Neural and Evolutionary Computation
free text keywords: Computer Science - Neural and Evolutionary Computing
Download from
21 references, page 1 of 2

[1] S. Kak, Feedback neural networks: new characteristics and a generalization. Circuits, Systems, and Signal Processing, vol. 12, pp. 263-278, 1993.

[2] K.C. Lingashetty, Active sites model for the B-matrix approach. 2010. arXiv:1006.4754 [3] S. Kak, Single neuron memories and the network‟s proximity matrix. 2009. arXiv:0906.0798 [4] J.J. Hopfield, Neural networks and physical systems with emergent collective computational properties. Proc. Nat. Acad. Sci. (USA), vol. 79, pp. 2554-2558, 1982. [OpenAIRE]

[5] D.L. Prados and S. Kak, Neural network capacity using the delta rule. Electronics Letters, vol. 25, pp. 197-199, 1989. [OpenAIRE]

[6] S. Kak, The three languages of the brain: quantum, reorganizational, and associative. In: K. Pribram, J. King (Eds.), Learning as Self- Organization, Lawrence Erlbaum, London, 1996, pp. 185-219.

[7] R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, The capacity of the Hopfield associative memory, IEEE Trans. Inform.Theory, vol. IT-33, pp. 461-482, 1987. [OpenAIRE]

[8] K.H. Pribram and J. L. King (eds.), Learning as Self-Organization. Mahwah, N. J.: L. Erlbaum Associates, 1996.

[9] D. Prados and S. Kak, Non-binary neural networks. Lecture Notes in Computing and Control, vol. 130, pp. 97-104, 1989.

[10] M. Schuster and K. K. Paliwal. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, vol. 45, pp. 2673-2681, 1997.

[11] C. Ji and D. Psaltis, Capacity of two-layer feedforward neural networks with binary weights. IEEE Trans. Inform. Theory, vol. 44, pp. 256-268, 1998.

[12] S. Kak, Can we define levels of artificial intelligence? Journal of Intelligent Systems, vol. 6, pp.133-144, 1996.

[13] S. Kak, Artificial and biological intelligence. ACM Ubiquity, vol. 6, number 42, pp. 1-20, 2005. [OpenAIRE]

[14] D.L. Schacter, Searching for Memory: The Brain, the Mind, and the Past. Basic Books, New York, 1997. [OpenAIRE]

[15] G.D.A. Brown, I. Neath, N. Chater, A ratio model of scale-invariant memory and identification. Psychological Review, vol. 114, pp. 539-576, 2007. [OpenAIRE]

[16] S. Kak, New training algorithm in feedforward neural networks, First International Conference on Fuzzy Theory and Technology, Durham, N. C., October 1992. Also in Wang, P.P. (Editor), Advance in fuzzy theory and technologies, Durham, N. C. Bookwright Press, 1993.

[17] S. Kak, A class of instantaneously trained neural networks, Information Sciences, 148, 97- 102, 2002. [OpenAIRE]

21 references, page 1 of 2
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue