Abstract
Associative memories are one of the most important field of artificial neural networks (ANN) [1–3]. They have been used as content addressable memories (CAM) which enable them to perform pattern recognition [4, 5] as well as mitigating wireless communications noise [6]. Few applications have been investigated [7] to interface the associative memory in order to make it practical CAM memory. Through this vision scope, the present paper is considered as an attempt for the implementation of such interface by suggesting the Pre-coding and Testing Technique (PTT). Furthermore, it will be shown that the suggested technique influences the retrieval capability of associative memories in particular the Bidirectional Associative Memory which is chosen as an application CAM for the validation and assessment of the proposed technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anderson, J.A.: A simple neural network generating interactive memory. Math. Biosci. 14, 197–220 (1972)
Nakano, K.: Associatron: a model of associative memory. IEEE Trans. Syst. Man Cybern. SMS-2, 380–388 (1972)
Yanai, H., Sawada, Y.: Associative memory network composed of neurons with hysteric property. Neural Netw. 3, 223–228 (1990)
Wang, Y., et al.: Bidirectional associative memory. In: Hassoun, M. (ed.), Associative Neural Memories: Theory and Implementation, p. 107. Oxford University Press, New York (1993)
Daniel, L., et al.: Biological plausibility of artificial neural networks: learning by non-hebbian synapses. In: Hassoun, M. (ed.) Associative Neural Memories: Theory and Implementation, p. 31. Oxford University Press, New York (1993)
Salavati, A.H., Raj Kumar, K., Shokrollahi, A., Gerstner, W.: Neural pre-coding increases the pattern retrieval capacity of Hopfield and Bidirectional Associative Memories. In: 2011 IEEE International Symposium on Information Theory Proceedings (ISIT), July 31 – August 5 2011, pp. 850–854 (2011)
Personnaz, L., et al.: Silicon integration of learning algorithms and other auto adaptive properties in a digital feedback network, VLSI design of neural networks. In: Ramacher, U., Ruckert, U. (eds.) Kluwer academic publisher (1991)
Rhee, M.Y.: Error Correcting Coding Theory. McGraw-Hill, New York (1989)
Fontanary, J.F., Koberle, R.: Neural Networks with transparent memory. J. Phys. A: Math. Gen. 21, 259–262 (1988)
Personnaz, L., et al.: Specification and implementation of a digital hopfield-type associative memory with on chip learning. IEEE Trans. Neural Netw. 3(4), 529–539 (1992)
Okajima, K., Tanaka, S., Fujiwara, S.: A heteroassociative memory network with feedback connection. In: Caudill, M., Butler, C. (eds.) Proceedings of the IEEE First International Conference on Neural Networks, vol. 2, pp. 711–718 (1987)
Hassoun, M.H.: Adaptive Dynamic heteroassociative neural memories for pattern classification. In: Proceedings of the SPIE, Optical Pattern Recognition, pp. 75–83 (1989)
Hassoun, M.H.: Dynamic heteroassociative neural memories. Neural Netw. 2(4), 275–287 (1989)
Leung, C.S., Cheung, K.F.: Householder encoding for discrete bidirectional associative memory. Proc. IJCNN 1, 237–241 (1991)
Kosko, B.: Adaptive bidirectional associative memories. Appl. Opt. 26, 4947–4960 (1987)
Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst. Man Cybern. SMC-18, 49–60 (1988)
Mishchenko, K.: Capacity of bidirectional associative memory. Contemp. Eng. Sci. 8, 825–833 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Saffih, F., Abdulllah, W., Ibrahim, Z. (2016). Pre-coding & Testing Technique for Interfacing Neural Networks Associative Memory. In: Cheng, L., Liu, Q., Ronzhin, A. (eds) Advances in Neural Networks – ISNN 2016. ISNN 2016. Lecture Notes in Computer Science(), vol 9719. Springer, Cham. https://doi.org/10.1007/978-3-319-40663-3_80
Download citation
DOI: https://doi.org/10.1007/978-3-319-40663-3_80
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-40662-6
Online ISBN: 978-3-319-40663-3
eBook Packages: Computer ScienceComputer Science (R0)