Abstract
Among the abilities that a sequence processing network should possess sequence disambiguation, that is, the ability to let temporal context information influence the evolution of the network dynamics, is one of the most important. In this work we propose an instance of the Bayesian Confidence Propagation Neural Network (BCPNN) that learns sequences with probabilistic associative learning and is able to disambiguate sequences with the use of synaptic traces (low pass filtered versions of the activity). We describe first how the BCPNN achieves both sequence recall and sequence learning from temporal input. Our main result is that the BCPNN network equipped with dynamical memory in the form of synaptic traces is capable of solving the sequence disambiguation problem in a reliable way. We characterize the relationship between the sequence disambiguation capabilities of the network and its dynamical parameters. Furthermore, we show that the inclusion of an additional fast synaptic trace greatly increases the network disambiguation capabilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lashley, K.: The problem of serial order in behavior. In: Cerebral Mechanisms in Behavior, pp. 112–136 (1951)
Koedijker, J.M., Oudejans, R.R., Beek, P.J.: Interference effects in learning similar sequences of discrete movements. J. Mot. Behav. 42(4), 209–222 (2010)
Panzer, S., Wilde, H., Shea, C.H.: Learning of similar complex movement sequences: proactive and retroactive effects on learning. J. Mot. Behav. 38(1), 60–70 (2006)
Agster, K.L., Fortin, N.J., Eichenbaum, H.: The hippocampus and disambiguation of overlapping sequences. J. Neurosci. 22(13), 5760–5768 (2002)
Levy, W.B.: A sequence predicting ca3 is a flexible associator that learns and uses context to solve hippocampal-like tasks. Hippocampus 6(6), 579–590 (1996)
Rajan, K., Harvey, C.D., Tank, D.W.: Recurrent network models of sequence generation and memory. Neuron 90(1), 128–142 (2016)
Sussillo, D., Abbott, L.F.: Generating coherent patterns of activity from chaotic neural networks. Neuron 63(4), 544–557 (2009)
Wang, Q., Rothkopf, C.A., Triesch, J.: A model of human motor sequence learning explains facilitation and interference effects based on spike-timing dependent plasticity. PLoS Comput. Biol. 13(8), e1005632 (2017)
Minai, A.A., Barrows, G.L., Levy, W.B.: Disambiguation of pattern sequences with recurrent networks. In: Proceedings WCNN, San Diego, vol. 4, pp. 176–180 (1994)
Samura, T., Hattori, M., Ishizaki, S.: Sequence disambiguation and pattern completion by cooperation between autoassociative and heteroassociative memories of functionally divided hippocampal CA3. Neurocomputing 71(16–18), 3176–3183 (2008)
Sohal, V.S., Hasselmo, M.E.: Gabab modulation improves sequence disambiguation in computational models of hippocampal region CA3. Hippocampus 8(2), 171–193 (1998)
Deco, G., Rolls, E.T.: Sequential memory: a putative neural and synaptic dynamical mechanism. J. Cogn. Neurosci. 17(2), 294–307 (2005)
Veliz-Cuba, A., Shouval, H.Z., Josić, K., Kilpatrick, Z.P.: Networks that learn the precise timing of event sequences. J. Comput. Neurosci. 39(3), 235–254 (2015)
Amari, S.I.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biol. Cybern. 27(2), 77–87 (1977)
Sandamirskaya, Y., Schöner, G.: An embodied account of serial order: how instabilities drive sequence generation. Neural Netw. 23(10), 1164–1179 (2010)
Bhalla, U.S.: Dendrites, deep learning, and sequences in the hippocampus. Hippocampus 29(3), 239–251 (2019)
Branco, T., Clark, B.A., Häusser, M.: Dendritic discrimination of temporal input sequences in cortical neurons. Science 329(5999), 1671–1675 (2010)
Fukushima, K.: A model of associative memory in the brain. Kybernetik 12(2), 58–63 (1973)
Guyon, I., Personnaz, L., Nadal, J., Dreyfus, G.: Storage and retrieval of complex sequences in neural networks. Phys. Rev. A 38(12), 6365 (1988)
Lansner, A., Ekeberg, Ö.: A one-layer feedback artificial neural network with a bayesian learning rule. Int. J. Neural Syst. 1(01), 77–87 (1989)
Tully, P.J., Hennig, M.H., Lansner, A.: Synaptic and nonsynaptic plasticity approximating probabilistic inference. Frontiers Synaptic Neurosci. 6, 8 (2014)
Douglas, R.J., Martin, K.A., Whitteridge, D.: A canonical microcircuit for neocortex. Neural Comput. 1(4), 480–488 (1989)
Douglas, R.J., Martin, K.A.: Neuronal circuits of the neocortex. Annu. Rev. Neurosci. 27, 419–451 (2004)
Lundqvist, M., Herman, P., Lansner, A.: Functional Brain Mapping and the Endeavor to Understand the Working Brain. IntechOpen (2013)
Lansner, A., Marklund, P., Sikström, S., Nilsson, L.G.: Reactivation in working memory: an attractor network model of free recall. PLoS ONE 8(8), e73776 (2013)
Martinez, R.H., Herman, P., Lansner, A.: Probabilistic associative learning suffices for learning the temporal structure of multiple sequences. BioRxiv, p. 545871 (2019)
Tully, P., Lindén, H., Hennig, M., Lansner, A.: Spike-based bayesian-hebbian learning of temporal sequences. PLoS Comput. Biol. 12(5), e1004954 (2016)
Self, M.W., Kooijmans, R.N., Supèr, H., Lamme, V.A., Roelfsema, P.R.: Different glutamate receptors convey feedforward and recurrent processing in macaque V1. Proc. Natl. Acad. Sci. 109(27), 11031–11036 (2012)
Jensen, O., Lisman, J.E.: Theta/gamma networks with slow NMDA channels learn sequences and encode episodic memory: role of NMDA channels in recall. Learn. Mem. 3(2–3), 264–278 (1996)
Wang, H., Stradtman, G.G., Wang, X.J., Gao, W.J.: A specialized NMDA receptor function in layer 5 recurrent microcircuitry of the adult rat prefrontal cortex. Proc. Natl. Acad. Sci. 105(43), 16791–16796 (2008)
Holthoff, K., Zecevic, D., Konnerth, A.: Rapid time course of action potentials in spines and remote dendrites of mouse visual cortex neurons. J. Physiol. 588(7), 1085–1096 (2010)
Zenke, F., Gerstner, W.: Hebbian plasticity requires compensatory processes on multiple timescales. Philos. Trans. Roy. Soc. B Biol. Sci. 372(1715), 20160259 (2017)
Fiete, I.R., Senn, W., Wang, C.Z., Hahnloser, R.H.: Spike-time-dependent plasticity and heterosynaptic competition organize networks to produce long scale-free sequences of neural activity. Neuron 65(4), 563–576 (2010)
Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179–211 (1990)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Hasson, U., Yang, E., Vallines, I., Heeger, D.J., Rubin, N.: A hierarchy of temporal receptive windows in human cortex. J. Neurosci. 28(10), 2539–2550 (2008)
Himberger, K.D., Chien, H.Y., Honey, C.J.: Principles of temporal processing across the cortical hierarchy. Neuroscience 389, 161–174 (2018)
Lansner, A., Benjaminsson, S., Johansson, C.: From ANN to biomimetic information processing. In: Gutiérrez, A., Marco, S. (eds.) Biologically Inspired Signal Processing for Chemical Sensing, pp. 33–43. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-00176-5_2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Martinez, R.H., Kviman, O., Lansner, A., Herman, P. (2019). Sequence Disambiguation with Synaptic Traces in Associative Neural Networks. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation. ICANN 2019. Lecture Notes in Computer Science(), vol 11727. Springer, Cham. https://doi.org/10.1007/978-3-030-30487-4_61
Download citation
DOI: https://doi.org/10.1007/978-3-030-30487-4_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30486-7
Online ISBN: 978-3-030-30487-4
eBook Packages: Computer ScienceComputer Science (R0)