paper-with-me

Papers

Deep Learning without Weight Symmetry

2024-05-31 · Li Ji-An, Marcus K. Benna

Backpropagation (BP), a foundational algorithm for training artificial neural networks, predominates in contemporary deep learning. Although highly successful, it is often considered biologically implausible. A significant limitation arises from the need for precise symmetry between connections in the backward and forward pathways to backpropagate gradient signals accurately, which is not observed in biological brains. Researchers have proposed several algorithms to alleviate this symmetry constraint, such as feedback alignment and direct feedback alignment. However, their divergence from backpropagation dynamics presents challenges, particularly in deeper networks and convolutional layers. Here we introduce the Product Feedback Alignment (PFA) algorithm. Our findings demonstrate that PFA closely approximates BP and achieves comparable performance in deep convolutional networks while avoiding explicit weight symmetry. Our results offer a novel solution to the longstanding weight symmetry problem, leading to more biologically plausible learning in deep convolutional networks compared to earlier methods.

📄 PDF Abstract BibTeX arXiv:2405.20594

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Symmetry-invariant optimization in deep networks

2015-11-05 · Vijay Badrinarayanan, Bamdev Mishra, Roberto Cipolla

Recent works have highlighted scale invariance or symmetry that is present in the weight space of a typical deep network and the adverse effect that it has on the Euclidean gradient based stochastic gradient descent opti…

Computational EfficiencyImage SegmentationSemantic Segmentation

Improving equilibrium propagation without weight symmetry through Jacobian homeostasis

2023-09-05 · Axel Laborieux, Friedemann Zenke

Equilibrium propagation (EP) is a compelling alternative to the backpropagation of error algorithm (BP) for computing gradients of neural networks on biological or analog neuromorphic substrates. Still, the algorithm req…

Understanding symmetries in deep networks

2015-11-03 · Vijay Badrinarayanan, Bamdev Mishra, Roberto Cipolla

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In …

Computational Efficiency

Benefits of mirror weight symmetry for 3D mesh segmentation in biomedical applications

2023-09-29 · Vladislav Dordiuk, Maksim Dzhigil, Konstantin Ushenin

3D mesh segmentation is an important task with many biomedical applications. The human body has bilateral symmetry and some variations in organ positions. It allows us to expect a positive effect of rotation and inversio…

Segmentation

SymNet: Symmetrical Filters in Convolutional Neural Networks

2019-06-10 · Gregory Dzhezyan, Hubert Cecotti

Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural netw…

image-classificationImage Classification