Credit Assignment in Neural Networks through Deep Feedback Control
OPEN ACCESS
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
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 biologicallyplausible 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 GaussNewton 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.
Permanent link
Publication status
published
Book title
Advances in Neural Information Processing Systems 34
Journal / series
Volume
Pages / Article No.
4674 - 4687
Publisher
Curran
Event
35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
09479 - Grewe, Benjamin / Grewe, Benjamin
Notes
Funding
173721 - Temporal Information Integration in Neural Networks (SNF)
189251 - Ultra compact miniaturized microscopes to image meso-scale brain activity (SNF)
186027 - Probabilistic learning in deep cortical networks (SNF)
189251 - Ultra compact miniaturized microscopes to image meso-scale brain activity (SNF)
186027 - Probabilistic learning in deep cortical networks (SNF)