Gradient learning in spiking neural networks by dynamic perturbation of conductances.

Keywords

Perturbation (astronomy), Artificial neural network, Computer science, Spiking neural network, Conductance

References

• International Joint Conference on Neural NetworksH. AMADOU BOUBACAR, Lecoeuche, S., S. Maouche — 1993
• Temporal and spatial properties of local circuits in neocortex.Alex M. Thomson, Jim Deuchars — 1994
• Methods in Neuronal Modelling. From Synapses to NetworksEric L. Schwartz — 1990
• Redistribution of synaptic efficacy between neocortical pyramidal neuronsHenry Markram, Misha Tsodyks — 1996
• Pattern-recognizing stochastic learning automataAndrew G. Barto, P. Anandan — 1985
• Learning in spiking neural networks by reinforcement of stochastic synaptic transmission.H. Sebastian Seung — 2003
• Learning in neural networks by reinforcement of irregular spiking.Xiaohui Xie, H. Sebastian Seung — 2004
• Introduction to real-time ray tracingPhilipp Slusallek, Peter Shirley, William R. Mark — 2005
• Gradient-based learning applied to document recognitionYann LeCun, Léon Bottou, Yoshua Bengio — 1998
• 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationBernard Widrow, Michael A. Lehr — 1990
• Reinforcement Learning: An IntroductionSutton, Richard S, Barto, Andrew G — 1998
• Neural NetsA.F. Rocha — 1992
• Gradient calculations for dynamic recurrent neural networks: a surveyBarak A. Pearlmutter — 1995
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward NetworksJustin Werfel, Xiaohui Xie, H. Sebastian Seung — 2003
• Model-free distributed learningAmir Dembo, T. Kailath — 1990
• Neural netsJoachim Ciesinger — 1988
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement LearningRonald J. Williams — 2004
• Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundationsDavid E. Rumelhart, James L. McClelland, AU — 1986
• Neural netsA.F. Rocha — 1992
• Advances in Neural Information ProcessingS. Baluja, D. Pomerleau — 1994

Cited by

• Reinforcement learning in populations of spiking neuronsRobert Urbanczik, Walter Senn — 2008
• Statistical Mechanics of On-line Node-perturbation LearningKazuyuki Hara, Kentaro Katahira, Kazuo Okanoya — 2010
• Indirect Training Algorithms for Spiking Neural Networks Controlled Virtual Insect NavigationXu Zhang — 2015
• Estimating or Propagating Gradients Through Stochastic NeuronsYoshua Bengio — 2013
• Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant RoboticsJeroen Burms, Ken Caluwaerts, Joni Dambre — 2015
• Synaptic dynamics: Linear model and adaptation algorithmAli Yousefi, Alireza A. Dibazar, Theodore W. Berger — 2014
• Robustness of Learning That Is Based on Covariance-Driven Synaptic PlasticityYonatan Loewenstein — 2008
• Spike-based Decision Learning of Nash Equilibria in Two-Player GamesJohannes Friedrich, Walter Senn — 2012
• Reinforcement learning of recurrent neural network for temporal codingDaichi Kimura, Yoshinori Hayakawa — 2006
• Neuron as a reward-modulated combinatorial switch and a model of learning behaviorM. Rvachev — 2011
• A bird’s eye view of neural circuit formationBence P. Ölveczky, Timothy J. Gardner — 2010
• Optimal node perturbation in linear perceptrons with uncertain eligibility traceKentaro Katahira, Tatsuya Cho, Kazuo Okanoya — 2010
• The Misbehavior of Reinforcement LearningGianluigi Mongillo, Hanan Shteingart, Yonatan Loewenstein — 2014
• Conductance-Based Neuron Models and the Slow Dynamics of ExcitabilityDaniel Soudry, Ron Meir — 2012
• Improved SpikeProp for using particle swarm optimizationFalah Y. H. Ahmed, Siti Mariyam Shamsuddin, Siti Zaiton Mohd Hashim — 2013
• Dynamics of Dual Prism Adaptation: Relating Novel Experimental Results to a Minimalistic Neural ModelOrlando Arévalo, Mona Bornschlegl, Sven Eberhardt — 2013
• Statistical mechanics of structural and temporal credit assignment effects on learning in neural networks.Hiroshi Saitō, Kentaro Katahira, Kazuo Okanoya — 2011
• Reinforcement Learning on Slow Features of High-Dimensional Input StreamsRobert Legenstein, Niko Wilbert, Laurenz Wiskott — 2010
• Interference and Shaping in Sensorimotor Adaptations with RewardsRan Darshan, Arthur Leblois, David Hansel — 2014
• Learning in Ultrametric Committee MachinesJuan Pablo Neirotti — 2012

Related papers

• A Hybrid Learning Rule for Efficient and Rapid Inference with Spiking Neural NetworksJibin Wu, Yansong Chua, Malu Zhang — 2019
• Spiking Neural Network (SNN) With Memristor Synapses Having Non-linear Weight UpdateTae-Yoon Kim, Suman Hu, Jaewook Kim — 2021
• A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP RuleYunzhe Hao, Xuhui Huang, Meng Dong — 2018
• Early Termination of STDP Learning with Spike Counts in Spiking Neural NetworksSunghyun Choi, Jongsun Park — 2020
• Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological AssembliesVahid Saranirad, Shirin Dora, T.M. McGinnity — 2022
• Dynamic Spike Bundling for Energy-Efficient Spiking Neural NetworksSarada Krithivasan, Sanchari Sen, Swagath Venkataramani — 2019
• A low-power Si:HfO2 ferroelectric tunnel memristor for spiking neural networksXiaobing Yan, Xiaotong Jia, Yinxing Zhang — 2022
• Initial synaptic weight distribution for fast learning speed and high recognition rate in STDP-based spiking neural networkJangsaeng Kim, Chul-Heung Kim, Sung Yun Woo — 2020
• A simple probabilistic spiking neuron model with Hebbian learning rulesTing Wu, Siyao Fu, Long Cheng — 2012
• Spike timing dependent plasticity based enhanced self-learning for efficient pattern recognition in spiking neural networksGopalakrishnan Srinivasan, Sourjya Roy, Vijay Raghunathan — 2017