×

Supervised learning with decision margins in pools of spiking neurons. (English) Zbl 1409.92047

Summary: Learning to categorise sensory inputs by generalising from a few examples whose category is precisely known is a crucial step for the brain to produce appropriate behavioural responses. At the neuronal level, this may be performed by adaptation of synaptic weights under the influence of a training signal, in order to group spiking patterns impinging on the neuron. Here we describe a framework that allows spiking neurons to perform such “supervised learning”, using principles similar to the support vector machine (SVM), a well-established and robust classifier. Using a hinge-loss error function, we show that requesting a margin similar to that of the SVM improves performance on linearly non-separable problems. Moreover, we show that using pools of neurons to discriminate categories can also increase the performance by sharing the load among neurons.

MSC:

92C20 Neural biology
68T05 Learning and adaptive systems in artificial intelligence

Software:

Scikit; Pynn; NEST
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abbott, L. F., & Nelson, S. B. (2000). Synaptic plasticity: taming the beast. Nature Neuroscience, 3 Suppl(november), 1178, 83.
[2] Altenmüller, E., Zimmermann, E., Schmidt, D., & Phil, S. (2013). Evolution of emotional communication: from sounds in nonhuman mammals to speech and music in man. Oxford: Oxford University Press. Retrieved from http://forward.library.wisconsin.edu/catalog/ocn810119047. · doi:10.1093/acprof:oso/9780199583560.001.0001
[3] Amit, D. J., Campbell, C., & Wong, K. Y. M. (1989). The interaction space of neural networks with sign-constrained synapses. Journal of Physics A: Mathematical and General, 22(21), 4687. · Zbl 0727.68091
[4] Bohte, S. M., Kok, J. N., & Poutrã, H. L. (2002). Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing, 48, 17-37. · Zbl 1006.68760 · doi:10.1016/S0925-2312(01)00658-0
[5] Clopath, C., Büsing, L., Vasilaki, E., & Gerstner, W. (2010). Connectivity reflects coding: a model of voltage-based STDP with homeostasis. Nature Neuroscience, 13(3), 344-52. · doi:10.1038/nn.2479
[6] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning. Retrieved from http://link.springer.com/article/10.1007/BF00994018 · Zbl 0831.68098
[7] Davison, A. A. P., Brüderle, D., Bruderle, D., Eppler, J., Kremkow, J., Muller, E., … Yger, P. (2009). PyNN: a common interface for neuronal network simulators. Frontiers in NeuroInformatics …, 2, 11. doi:10.3389/neuro.11.011.2008
[8] Diesmann, M., & Gewaltig, M. O. (2007). NEST (NEural simulation tool). Scholarpedia. doi:10.4249/scholarpedia.1430. · doi:10.4249/scholarpedia.1430
[9] Eccles, S. J. C., Itō, M., & Szentágothai, J. (1967). The cerebellum as a neuronal machine (p. 335). Retrieved from http://books.google.fr/books/about/The_cerebellum_as_a_neuronal_machine.html?id=nWh9AAAAIAAJ&pgis=1
[10] El Boustani, S., Yger, P., Frégnac, Y., & Destexhe, A. (2012). Stable learning in stochastic network states. The Journal of Neuroscience: The Official Journal of the Society for Neuroscience, 32(1), 194-214. · Zbl 1446.92097
[11] Florian, R. V. (2007). Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity. Neural Computation, 19(6), 1468-502. · Zbl 1115.68473 · doi:10.1162/neco.2007.19.6.1468
[12] Florian, R. V. (2012). The chronotron: a neuron that learns to fire temporally precise spike patterns. PloS One, 7(8), e40233. · doi:10.1371/journal.pone.0040233
[13] Gardner, E. (1988). The space of interactions in neural network models. Journal of Physics A: Mathematical and General, 21(July 1987), 257-270. · Zbl 1128.82302 · doi:10.1088/0305-4470/21/1/030
[14] Gutig, R., & Sompolinsky, H. (2006). The tempotron: a neuron that learns spike timing-based decisions. Nature Neuroscience, 9(3), 420-428. · doi:10.1038/nn1643
[15] Gütig, R., & Sompolinsky, H. (2009). Time-warp-invariant neuronal processing. PLoS Biology, 7(7), e1000141. · doi:10.1371/journal.pbio.1000141
[16] Holmes, W. G. (1986). Kin recognition by phenotype matching in female Belding’s ground squirrels. Animal Behaviour, 34, 38-47. · doi:10.1016/0003-3472(86)90004-7
[17] Izhikevich, E. M. (2007). Solving the distal reward problem through linkage of STDP and dopamine signaling. Cerebral Cortex (New York, N.Y.: 1991), 17(10), 2443-52. · doi:10.1093/cercor/bhl152
[18] Kentros, C. G., Agnihotri, N. T., Streater, S., Hawkins, R. D., & Kandel, E. R. (2004). Increased attention to spatial context increases both place field stability and spatial memory. Neuron, 42(2), 283-295. · doi:10.1016/S0896-6273(04)00192-8
[19] Legenstein, R., & Maass, W. (2007). On the classification capability of sign-constrained perceptrons. Neural Computation, 20(1), 288-309. · Zbl 1148.92009 · doi:10.1162/neco.2008.20.1.288
[20] Legenstein, R., Naeger, C., & Maas, W. (2005). What can a neuron learn with spike-timing-dependent plasticity? Neural Computation, 17(11), 2337-2382. · Zbl 1075.68635
[21] Legenstein, R., Pecevski, D., & Maass, W. (2008). A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback. PLoS Computational Biology, 4(10), e1000180. · doi:10.1371/journal.pcbi.1000180
[22] Marr, D. (1969). A theory of cerebellar cortex. The Journal of Physiology, 202(2), 437-470.
[23] Masquelier, T., Guyonneau, R., & Thorpe, S. J. (2009). Competitive STDP-based spike pattern learning. Neural Computation, 21(5), 1259-1276. · Zbl 1160.92315
[24] Pape, H. H., & Pare, D. (2010). Plastic synaptic networks of the amygdala for the acquisition, expression, and extinction of conditioned fear. Physiological Reviews, 90(2), 419-463. · doi:10.1152/physrev.00037.2009
[25] Pedregosa, F., & Varoquaux, G. (2011). Scikit-learn: Machine learning in Python. … of Machine Learning …, 12, 2825-2830. · Zbl 1280.68189
[26] Pfister, J., Toyoizumi, T., Barber, D., & Gerstner, W. (2006). Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning. Neural Computation, 18(6), 1318-48. · Zbl 1092.92008 · doi:10.1162/neco.2006.18.6.1318
[27] Ponulak, F., & Kasiński, A. (2010). Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Computation, 22(2), 467-510. · Zbl 1183.92018 · doi:10.1162/neco.2009.11-08-901
[28] Raymond, J. L., Lisberger, S. G., & Mauk, M. D. (1996). The cerebellum. Science, 272, 1126-1131. · doi:10.1126/science.272.5265.1126
[29] Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386-408. · doi:10.1037/h0042519
[30] Sweatt, J. D. (2009). Mechanisms of Memory, Second Edition (p. 450). Academic Press. Retrieved from http://www.amazon.com/Mechanisms-Memory-Second-Edition-Sweatt/dp/0123749514
[31] Urbanczik, R., & Senn, W. (2009). Reinforcement learning in populations of spiking neurons. Nature Neuroscience, 12(3), 250-2. · doi:10.1038/nn.2264
[32] Xu, Y., Zeng, X., & Zhong, S. (2013). A new supervised learning algorithm for spiking neurons. Neural Computation, 25(6), 1472-511. · Zbl 1448.92051 · doi:10.1162/NECO_a_00450
[33] Yger, P., & Harris, K. D. (2013). The Convallis rule for unsupervised learning in cortical networks. PLoS Computational Biology, 9(10), 1-32. · doi:10.1371/journal.pcbi.1003272
[34] Yin, H. H., & Knowlton, B. J. (2006). The role of the basal ganglia in habit formation. Nature Reviews Neuroscience, 7(6), 464-476. · doi:10.1038/nrn1919
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.