STDP-compatible approximation of backpropagation in an energy-based model

Neural Computation

Volumn 29, Issue 3, 2017, Pages 555-577

  Bengio, Yoshua ^a,b   Mesnard, Thomas ^c   Fischer, Asja ^d   Zhang, Saizheng ^a   Wu, Yuhuai ^e  

^a UNIVERSITÉ DE MONTRÉAL   (Canada)

^b CANADIAN INSTITUTE FOR ADVANCED RESEARCH   (Canada)

^c ECOLE NORMALE SUPÉRIEURE   (France)

^d UNIVERSITY OF BONN   (Germany)

^e UNIVERSITY OF TORONTO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION THEORY; ERRORS; MARKOV PROCESSES; NEURONS;

APPROXIMATE INFERENCE; ENERGY-BASED MODELS; ERROR BACK-PROPAGATION; MARKOV CHAIN MONTE-CARLO; NEURAL COMPUTATIONS; SPIKE TIMING DEPENDENT PLASTICITIES; TEMPORAL DERIVATIVES; THEORETICAL ARGUMENTS;

BACKPROPAGATION;

EID: 85013683708     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/NECO_a_00934     Document Type: Article

References (33)

1. Alain, G., & Bengio, Y. (2013). What regularized auto-encoders learn from the data generating distribution. In Proceedings of the International Conference on Learning Representations. arXiv:1211.4246
2. Andrieu, C., de Freitas, N., Doucet, A., & Jordan, M. (2003). An introduction to MCMC for machine learning. Machine Learning, 50, 5-43.
3. Arora, S., Liang, Y., & Ma, T. (2015). Why are deep nets reversible? A simple theory, with implications for training (Technical Report). arXiv:1511.05653
4. Berkes, P., Orban, G., Lengyel, M., & Fiser, J. (2011). Spontaneous cortical activity reveals hallmarks of an optimal internal model of the environment. Science, 331, 83-87.
5. Bi, G.-q., & Poo, M.-m. (1998). Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. Journal of Neuroscience, 18(24), 10464-10472.
6. Bi, G., & Poo, M. (2001). Synaptic modification by correlated activity: Hebb's postulate revisited. Annu. Rev. Neurosci., 24, 139-166.
7. Bienenstock, E. L., Cooper, L. N., & Munro, P.W. (1982). Theory for the development of neuron selectivity: Orientation specificity and binocular interaction in visual cortex. Journal of Neuroscience, 2, 32-48.
8. Feldman, D. E. (2012). The spike timing dependence of plasticity. Neuron, 75(4), 556-571.
9. Fiete, I. R., & Seung, H. S. (2006). Gradient learning in spiking neural networks by dynamic perturbations of conductances. Physical Review Letters, 97(4), 048104.
10. Friston, K. J., & Stephan, K. E. (2007). Free-energy and the brain. Synthese, 159, 417-458.
11. Froemke, R. C., & Dan, Y. (2002). Spike-timing-dependent synaptic modification induced by natural spike trains. Nature, 416(6879), 433-438.
12. Gerstner, W., Kempter, R., vanHemmen, J., & Wagner, H. (1996).Aneuronal learning rule for sub-millisecond temporal coding. Nature, 386, 76-78.
13. Gjorgjievaa, J., Clopath, C., Audet, J., & Pfister, J.-P. (2011). A triplet spike-timing dependent plasticity model generalizes the Bienenstock-Cooper-Munro rule to higher-order spatiotemporal correlations. Proceedings of the National Academy of Sciences, USA, 108(48), 19383-19388.
14. Hinton, G. E. (2007). How to do backpropagation in a brain. Invited talk at theNIPS'2007 Deep LearningWorkshop.
15. Hinton, G. E. (2016). Can the brain do back-propagation? Invited talk at Stanford University Colloquium on Computer Systems. https://www.youtube.com/watch?v=VIRCybGgHts
16. Hinton, G. E., & McClelland, J. L. (1988). Learning representations by recirculation. In D. Z. Anderson (Ed.), Neural information processing systems (pp. 358-366). College Park, MD: American Institute of Physics.
17. Hinton, G. E., & Sejnowski, T. J. (1986). Learning and relearning in Boltzmann machines. In D. E. Rumelhart & J. L.McClelland (Eds.), Parallel distributed processing: Explorations in the microstructure of cognition. Vol. 1: Foundations (pp. 282-317). Cambridge, MA: MIT Press.
18. Hopfield, J. J. (1984). Neurons with graded responses have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences, USA, 81, 3088-3092.
19. Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016). Binarized neural networks. In D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, & R. Garnett (Eds.), Advances in neural information processing systems, 29 (pp. 4107-4115). Red Hook, NY: Curran.
20. Intrator, N., & Cooper, L. N. (1992). Objective function formulation of the BCM theory of visual cortical plasticity: Statistical connections, stability conditions. Neural Networks, 5, 3-17.
21. Lillicrap, T. P., Cownden, D., Tweed, D. B., & Akerman, C. J. (2014). Random feedback weights support learning in deep neural networks. arXiv:1411.0247
22. Markram, H., Gerstner, W., & Sjöström, P. (2012). Spike-timing-dependent plasticity: A comprehensive overview. Frontiers in Synaptic Plasticity, 4(2), 8.
23. Markram, H., Lübke, J., Frotscher, M., & Sakmann, B. (1997). Regulation of synaptic efficacy by coincidence of postsynaptic aps and EPSPS. Science, 275(5297), 213-215.
24. Markram, H., & Sakmann, B. (1995). Action potentials propagating back into dendrites triggers changes in efficacy. Soc. Neurosci. Abs., 21, 2007.
25. Morrison, A., Diesmann, M., & Gerstner, W. (2008). Phenomenological models of synaptic plasticity based on spike timing. Biological Cybernetics, 98(6), 459-478.
26. Rezende, D. J., & Gerstner, W. (2014). Stochastic variational learning in recurrent spiking networks. Frontiers in Computational Neuroscience, 8(38).
27. Scellier, B., & Bengio, Y. (2016). Equilibrium propagation: Bridging the gap between energy-based models and backpropagation. arXiv:1602.05179
28. Shepherd, G. M. (2003). The synaptic organization of the brain. New York: Oxford University Press.
29. Van Rossum, M. C., Bi, G. Q., & Turrigiano, G. G. (2000). Stable Hebbian learning fromspike timing-dependent plasticity. Journal of Neuroscience, 20(23), 8812-8821.
30. Vincent, P. (2011). A connection between score matching and denoising autoencoders. Neural Computation, 23(7), 1661-1674.
31. Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P.-A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Machine Learning Res., 11, 3371-3408.
32. Williams, R. J. (1992). Simple statistical gradient-following algorithms connectionist reinforcement learning. Machine Learning, 8, 229-256.
33. Xie, X., & Seung, H. S. (2000). Spike-based learning rules and stabilization of persistent neural activity. In S. Solla, T. Leen, & K. Müller (Eds.), Advances in neural information processing systems, 12 (pp. 199-208). Cambridge, MA: MIT Press.