Credit Assignment in Neural Networks through Deep Feedback Control
- URL: http://arxiv.org/abs/2106.07887v1
- Date: Tue, 15 Jun 2021 05:30:17 GMT
- Title: Credit Assignment in Neural Networks through Deep Feedback Control
- Authors: Alexander Meulemans, Matilde Tristany Farinha, Javier Garc\'ia
Ord\'o\~nez, Pau Vilimelis Aceituno, Jo\~ao Sacramento, Benjamin F. Grewe
- Abstract summary: Deep Feedback Control (DFC) is 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 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.
- Score: 59.14935871979047
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 motives, 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.
Related papers
- Contrastive Learning in Memristor-based Neuromorphic Systems [55.11642177631929]
Spiking neural networks have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks.
In this work, we design and investigate a proof-of-concept instantiation of contrastive-signal-dependent plasticity (CSDP), a neuromorphic form of forward-forward-based, backpropagation-free learning.
arXiv Detail & Related papers (2024-09-17T04:48:45Z) - Statistical Physics of Deep Neural Networks: Initialization toward
Optimal Channels [6.144858413112823]
In deep learning, neural networks serve as noisy channels between input data and its representation.
We study a frequently overlooked possibility that neural networks can be intrinsic toward optimal channels.
arXiv Detail & Related papers (2022-12-04T05:13:01Z) - Minimizing Control for Credit Assignment with Strong Feedback [65.59995261310529]
Current methods for gradient-based credit assignment in deep neural networks need infinitesimally small feedback signals.
We combine strong feedback influences on neural activity with gradient-based learning and show that this naturally leads to a novel view on neural network optimization.
We show that the use of strong feedback in DFC allows learning forward and feedback connections simultaneously, using a learning rule fully local in space and time.
arXiv Detail & Related papers (2022-04-14T22:06:21Z) - Learn Like The Pro: Norms from Theory to Size Neural Computation [3.848947060636351]
We investigate how dynamical systems with nonlinearities can inform the design of neural systems that seek to emulate them.
We propose a Learnability metric and quantify its associated features to the near-equilibrium behavior of learning dynamics.
It reveals exact sizing for a class of neural networks with multiplicative nodes that mimic continuous- or discrete-time dynamics.
arXiv Detail & Related papers (2021-06-21T20:58:27Z) - Learning Structures for Deep Neural Networks [99.8331363309895]
We propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience.
We show that sparse coding can effectively maximize the entropy of the output signals.
Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure.
arXiv Detail & Related papers (2021-05-27T12:27:24Z) - Learning in Deep Neural Networks Using a Biologically Inspired Optimizer [5.144809478361604]
We propose a novel biologically inspired for artificial (ANNs) and spiking neural networks (SNNs)
GRAPES implements a weight-distribution dependent modulation of the error signal at each node of the neural network.
We show that this biologically inspired mechanism leads to a systematic improvement of the convergence rate of the network, and substantially improves classification accuracy of ANNs and SNNs.
arXiv Detail & Related papers (2021-04-23T13:50:30Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z) - A Theoretical Framework for Target Propagation [75.52598682467817]
We analyze target propagation (TP), a popular but not yet fully understood alternative to backpropagation (BP)
Our theory shows that TP is closely related to Gauss-Newton optimization and thus substantially differs from BP.
We provide a first solution to this problem through a novel reconstruction loss that improves feedback weight training.
arXiv Detail & Related papers (2020-06-25T12:07:06Z) - Equilibrium Propagation for Complete Directed Neural Networks [0.0]
Most successful learning algorithm for artificial neural networks, backpropagation, is considered biologically implausible.
We contribute to the topic of biologically plausible neuronal learning by building upon and extending the equilibrium propagation learning framework.
arXiv Detail & Related papers (2020-06-15T22:12:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.