Credit Assignment in Neural Networks through Deep Feedback ControlDownload PDF

21 May 2021, 20:49 (modified: 24 Jan 2022, 08:22)NeurIPS 2021 SpotlightReaders: Everyone
Keywords: Biologically-plausible Deep Learning, Neuroscience, Deep Learning, Control theory, Optimization theory
TL;DR: We introduce Deep Feedback Control, a new bio-plausible learning method that uses a feedback controller to drive a deep neural network to match a desired output target and which approximates Gauss-Newton optimization.
Abstract: The success of deep learning sparked interest in whether the brain learns by using similar techniques for assigning credit to each synaptic weight for its contribution to the network output. However, the majority of current attempts at biologically-plausible learning methods are either non-local in time, require highly specific connectivity motifs, or have no clear link to any known mathematical optimization method. Here, we introduce Deep Feedback Control (DFC), a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. The resulting learning rule is fully local in space and time and approximates Gauss-Newton optimization for a wide range of feedback connectivity patterns. To further underline its biological plausibility, we relate DFC to a multi-compartment model of cortical pyramidal neurons with a local voltage-dependent synaptic plasticity rule, consistent with recent theories of dendritic processing. By combining dynamical system theory with mathematical optimization theory, we provide a strong theoretical foundation for DFC that we corroborate with detailed results on toy experiments and standard computer-vision benchmarks.
Supplementary Material: pdf
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: https://github.com/meulemansalex/deep_feedback_control
16 Replies

Loading