Abstract
In this paper, we proposed an extended version of binary code selection algorithm (BCSA) for the variable-order prediction by introducing multiple distal dendrites into BCSA. The proposed model of artificial neurons has a single proximal dendrite to receive the feed-forward inputs (sequences) from the world and multiple distal dendrites to receive the horizontal inputs from nearby neurons. During training, each distal dendrite is able to remember the states of neurons activated at different time and store the temporal correlations. After training, each distal dendrite independently recalls the temporal correlations contained in sequences and makes a local prediction. The variable-order prediction can be obtained by combining these local predictions made by multiple distal dendrites. Experiments show that the proposed method outperforms BCSA and other methods, such as back-propagation networks and radial basis function networks, especially while processing complex sequences.
Similar content being viewed by others
References
Hawkins J, Blakeslee S (2007) On intelligence. Macmillan, London
Mountcastle VB (1997) The columnar organization of the neocortex. Brain 120(4):701–722
Stuart G, Spruston N, Häusse M (2008) Dendrites. Oxford University Press, Oxford
Rall W (1967) Distinguishing theoretical synaptic potentials computed for different soma-dendritic distributions of synaptic input. J Neurophysiol 30(5):1138–1168
Rall W, Burke R, Smith T, Nelson PG, Frank K (1967) Dendritic location of synapses and possible mechanisms for the monosynaptic epsp in motoneurons. J Neurophysiol 30(5):884–915
Rall W, Shepherd GM (1968) Theoretical reconstruction of field potentials and dendrodendritic synaptic interactions in olfactory bulb. J Neurophysiol 31(6):884–915
Segev I (2006) What do dendrites and their synapses tell the neuron? J Neurophysiol 95(3):1295–1297
Hoekstra J, Rouw E (2000) Modeling of dendritic computation: the single dendrite. In: Computing anticipatory systems: CASYS’99-third international conference, vol 517. AIP Publishing, pp 308–322
Tang Z, Tamura H, Kuratu M, Ishizuka O, Tanno K (2001) A model of the neuron based on dendrite mechanisms. Electron Commun Jpn (Part III: Fundam Electron Sci) 84(8):11-24
Liu G (2004) Local structural balance and functional interaction of excitatory and inhibitory synapses in hippocampal dendrites. Nat Neurosci 7(4):373–379
Gasparini S, Magee JC (2006) State-dependent dendritic computation in hippocampal ca1 pyramidal neurons. J Neurosci 26(7):2088–2100
Spruston N (2008) Pyramidal neurons: dendritic structure and synaptic integration. Nat Rev Neurosci 9(3):206–221
Knoblauch A (2009) Structural plasticity, cortical memory, and the spacing effect. BMC Neurosci 10(Suppl1):O16
Blasio Gd, Moreno Díaz A, Moreno Díaz R (2011) Dendritic-like reliable computation in artificial neurons. In: Actas de la 13th international conference on computer aided systems theory, EUROCAST 2011. Instituto Universitario de Ciencias y Tecnologías Cibernéticas, pp 66–68
Sha Z, Hu L (2012) The algorithm improvement of the neuron model based on dendrites mechanism. Int J Comput Sci Netw Secur 12(10):1–5
Gollo LL, Kinouchi O, Copelli M (2013) Single-neuron criticality optimizes analog dendritic computation. Sci Rep 3(11):3222–3222
George S, Hasler J, Koziol S, Nease S, Ramakrishnan S (2013) Low power dendritic computation for wordspotting. J Low Power Electron Appl 3(2):73–98
Butz M, van Ooyen A (2013) A simple rule for dendritic spine and axonal bouton formation can account for cortical reorganization after focal retinal lesions. PLoS Comput Biol 9(10):e1003259
Chen X, Sneyd J (2014) A computational model of the dendron of the gnrh neuron. Bull Math Biol 77(6):1–23
Montegranario H, Espinosa J (2014) Radial basis functions. In: Variational regularization of 3D data. Springer, New York, pp 69–81
Balabin RM, Lomakina EI (2011) Support vector machine regression (SVR/LS-SVM) an alternative to neural networks (ANN) for analytical chemistry? comparison of nonlinear methods on near infrared (NIR) spectroscopy data. Analyst 136(8):1703–1712
Sato T, Uchida G, Tanifuji M (2009) Cortical columnar organization is reconsidered in inferior temporal cortex. Cerebral Cortex 19(8):1870–1888
Hoyer PO, Hyvärinen A (2002) A multi-layer sparse coding network learns contour coding from natural images. Vision Research 42(12):1593–1605
Hawkins J, Ahmad S, Dubinsky D (2012) Hierarchical temporal memory including htm cortical learning algorithms. Techical Report
Olshausen BA, Field DJ (2004) Sparse coding of sensory inputs. Curr Opin Neurobiol 14(4):481–487
Attwell D, Laughlin SB (2001) An energy budget for signaling in the grey matter of the brain. J Cereb Blood Flow Metab 21(10):1133–1145
Lennie P (2003) The cost of cortical computation. Curr Biol 13(6):493–497
Olshausen BA et al (1996) Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583):607–609
Changizi MA (2001) Universal scaling laws for hierarchical complexity in languages, organisms, behaviors and other combinatorial systems. J Theor Biol 211(3):277–295
Rivest RL, Sloan R (1994) A formal model of hierarchical concept-learning. Inf Comput 114(1):88–114
Simon HA (1996) Sciences of the artificial, vol 136. MIT Press, Cambridge
George D, Hawkins J (2009) Towards a mathematical theory of cortical micro-circuits. PLoS Comput Biol 5(10):e1000532
Bobier BA, Wirth M (2008) Content-based image retrieval using hierarchical temporal memory. In: Proceedings of the 16th ACM international conference on multimedia. ACM, pp 925–928
Starzyk JA, He H (2009) Spatio-temporal memories for machine learning: a long-term memory organization. Neural Netw IEEE Trans 20(5):768–780
Starzyk JA, He H (2007) Anticipation-based temporal sequences learning in hierarchical structure. Neural Netw IEEE Trans 18(2):344–358
Mountcastle VB (1978) An organizing principle for cerebral function: the unit model and the distributed system. MIT Press, Cambridge
Horton JC, Adams DL (2005) The cortical column: a structure without a function. Philos Trans R Soc B: Biol Sci 360(1456):837–862
Rinkus GJ (2010) A cortical sparse distributed coding model linking mini-and macrocolumn-scale functionality. Front Neuroanat 4(2):1–13
Kuang Y, Zhang Y, Zhang L (2013) An improved code selection algorithm for fault prediction. Neural Comput Appl 22(7–8):1763–1772
Hawkins J, George D (2011) Hierarchical temporal memory: concepts, theory and terminology. Whitepaper, Numenta Inc, Hayes
Pradhan B, Lee S (2010) Landslide susceptibility assessment and factor e?ect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environ Model Softw 25(6):747–759
Shifei D, Gang M, Zhongzhi S (2014) A rough RBF neural network based on weighted regularized extreme learning machine. Neural Process Lett 40(3):245–260
Zhizheng L, Ning L (2014) Efficient feature scaling for support vector machines with a quadratic kernel. Neural Process Lett 39(3):235–246
Hebb DO (2002) The organization of behavior: a neuropsychological theory. Psychology Press, Routledge
Rinkus GJ (1986) A combinatorial neural network exhibiting episodic and semantic memory properties for spatio-temporal patterns. Dissertation, Boston University
Willerman L, Schultz R, Rutledge JN, Bigler ED (1991) In vivo brain size and intelligence. Intelligence 15(2):223–228
Acknowledgments
This work was supported by China Postdoctoral Science Foundation under Grant No. 2014M560730, National Nature Science Foundation of China under Grant No. 61304187, Science Foundation of Science & Technology Department of Sichuan Province under Grant No. 2015JY0071, and Nature Science Foundation of Chengdu Normal University under Grants Nos. CS14ZD02 and YJRC2014-9.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhou, X., Tang, N., Kuang, Y. et al. An approach to variable-order prediction via multiple distal dendrites of neurons. Neural Comput & Applic 29, 1–12 (2018). https://doi.org/10.1007/s00521-016-2518-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2518-y