bioRxiv (Cold Spring Harbor Laboratory) · 2019 · 57 citations · 42 references
Life SciencesComputer ScienceNeuroscienceComputational NeuroscienceMachine LearningSynaptic PlasticityDeep LearningLearning In Neural SystemsLearning SystemsNeural NetworksNeuronal DynamicsSpiking Neural NetworksBackpropagation Through TimeDeep Reinforcement LearningEnergy-efficient ComputationGradient DescentNeuromorphic HardwareRecurrent Neural NetworksRecurrent Spiking Neural NetworksSpiking Neuron Models
Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain, yet how they learn via synaptic plasticity to perform complex computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. The learning method—called e‑prop—approaches the performance of backpropagation through time and suggests a method for powerful on‑chip learning in energy‑efficient spike‑based hardware for artificial intelligence.
Abstract Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. Yet in spite of extensive research, how they can learn through synaptic plasticity to carry out complex network computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This learning method–called e-prop–approaches the performance of backpropagation through time (BPTT), the best-known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in energy-efficient spike-based hardware for artificial intelligence.
42
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
Speech recognition with deep recurrent neural networks
Alex Graves, Abdelrahman Mohamed, Geoffrey E. Hinton · 2013 · 8.8K citations
Klaus Greff, Rupesh K. Srivastava, Jan Koutník et al. · IEEE Transactions on Neural Networks and Learning Systems · 2016 · 6.8K citations · Full text
Backpropagation through time: what it does and how to do it
Paul J. Werbos · Proceedings of the IEEE · 1990 · 4.9K citations