Abstract
Sequential information processing, for instance the sequence memory, plays an important role on many functions of brain. In this paper, multi-sequence memory with controllable steady-state period and high sequence storage capacity is proposed. By introducing a novel exponential kernel sampling function and the sampling interval parameter, the steady-state period can be controlled, and the steady-state time steps are equal to the sampling interval parameter. Furthermore, we explained this phenomenon theoretically. Ascribing to the nonlinear function constitution for local field, the conventional Hebbian learning rule with linear outer product method can be improved. Simulation results show that neural network with nonlinear function constitution can effectively increase sequence storage capacity.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Anderson J (1995) Learning and memory. Wiley, New York
Laurent G et al (2001) Odor encoding as an active, dynamical process: experiments, computation, and theory. Annu Rev Neurosci 24:263–297
Hahnloser RHR et al (2002) An ultra-sparse code underlies the generation of neural sequences in a songbird. Nature 419:65–70
Selverston A (1999) General principles of rhythmic motor pattern generation derived from invertebrate CPGs. Prog Brain Res 123:247–257
Melamed O et al (2004) GABAergic microcircuits in the neostriatum. Trends Neurosci 27(11):662–669
Anderson JA (1972) A simple neural network generating interactive memory. Math Biosci 14:197–220
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computation abilities. Proc Nat Acad Sci 79:2445–2558
Amari S (1989) Characteristics of sparsely encoded associative memory. Neural Netw 2:451–457
Kohonen T (1972) Correlation matrix memories. IEEE Trans Comput C-21:353–359
Sandberg A, Lansner A (2002) Synaptic depression as an intrinsic driver of reinstatement dynamics in an attractor network. Neurocomputing 44–46:615–622
Sompolinsky H, Kanter I (1986) Temporal association in asymmetric neural networks. Phys Rev Lett 57:2861–2864
Seliger P, Tsimring LS, Rabinnovich MI (2003) Dynamics-based sequential memory: winnerless competition of patterns. Phys Rev E 67:011905
Rehn M, Lansner A (2004) Sequence memory with dynamical synapses. Neurocomputing 58–60:271–278
Tank DW, Hopfield JJ (1987) Neural computation by concentrating information in time. Proc Nat Acad Sci 84:1896–1900
Kleinfeld D (1986) Sequential state generation by model neural networks. Proc Nat Acad Sci 83:9469–9473
Gutfreund H, Mezard M (1988) Processing of temporal sequences in neural networks. Phys Rev Lett 61:235–238
Lawrence M, Trappenberg T, Fine A (2006) Rapid learning and robust recall of long sequences in modular associator networks. Neurocomputing 69:634–641
Huerta R, Rabinovich M (2004) Reproducible sequence generation in random neural ensembles. Phys Rev Lett 93:238104
Masato O (1996) Notions of associative memory and sparse coding. Neural Netw 9(8):1429–1458
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported by the National Natural Science Foundation of PR China (60874113).
Rights and permissions
About this article
Cite this article
Xia, M., Tang, Y., Fang, J. et al. Efficient multi-sequence memory with controllable steady-state period and high sequence storage capacity. Neural Comput & Applic 20, 17–24 (2011). https://doi.org/10.1007/s00521-010-0453-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-010-0453-x