Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass

Giorgia Dellaferrera, Gabriel Kreiman
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:4937-4955, 2022.

Abstract

Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign symmetry, feedback alignment, and direct feedback alignment, but they invariably rely on a backward pass that hinders the possibility of solving all the issues simultaneously. Here, we propose to replace the backward pass with a second forward pass in which the input signal is modulated based on the error of the network. We show that this novel learning rule comprehensively addresses all the above-mentioned issues and can be applied to both fully connected and convolutional models. We test this learning rule on MNIST, CIFAR-10, and CIFAR-100. These results help incorporate biological principles into machine learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-dellaferrera22a, title = {Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass}, author = {Dellaferrera, Giorgia and Kreiman, Gabriel}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {4937--4955}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/dellaferrera22a/dellaferrera22a.pdf}, url = {https://proceedings.mlr.press/v162/dellaferrera22a.html}, abstract = {Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign symmetry, feedback alignment, and direct feedback alignment, but they invariably rely on a backward pass that hinders the possibility of solving all the issues simultaneously. Here, we propose to replace the backward pass with a second forward pass in which the input signal is modulated based on the error of the network. We show that this novel learning rule comprehensively addresses all the above-mentioned issues and can be applied to both fully connected and convolutional models. We test this learning rule on MNIST, CIFAR-10, and CIFAR-100. These results help incorporate biological principles into machine learning.} }
Endnote
%0 Conference Paper %T Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass %A Giorgia Dellaferrera %A Gabriel Kreiman %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-dellaferrera22a %I PMLR %P 4937--4955 %U https://proceedings.mlr.press/v162/dellaferrera22a.html %V 162 %X Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of applications, it lacks biological plausibility in many regards, including the weight symmetry problem, the dependence of learning on non-local signals, the freezing of neural activity during error propagation, and the update locking problem. Alternative training schemes have been introduced, including sign symmetry, feedback alignment, and direct feedback alignment, but they invariably rely on a backward pass that hinders the possibility of solving all the issues simultaneously. Here, we propose to replace the backward pass with a second forward pass in which the input signal is modulated based on the error of the network. We show that this novel learning rule comprehensively addresses all the above-mentioned issues and can be applied to both fully connected and convolutional models. We test this learning rule on MNIST, CIFAR-10, and CIFAR-100. These results help incorporate biological principles into machine learning.
APA
Dellaferrera, G. & Kreiman, G.. (2022). Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:4937-4955 Available from https://proceedings.mlr.press/v162/dellaferrera22a.html.

Related Material