paper-with-me

Papers

Hebbian Deep Learning Without Feedback

2022-09-23 · Adrien Journé, Hector Garcia Rodriguez, Qinghai Guo, Timoleon Moraitis

Recent approximations to backpropagation (BP) have mitigated many of BP's computational inefficiencies and incompatibilities with biology, but important limitations still remain. Moreover, the approximations significantly decrease accuracy in benchmarks, suggesting that an entirely different approach may be more fruitful. Here, grounded on recent theory for Hebbian learning in soft winner-take-all networks, we present multilayer SoftHebb, i.e. an algorithm that trains deep neural networks, without any feedback, target, or error signals. As a result, it achieves efficiency by avoiding weight transport, non-local plasticity, time-locking of layer updates, iterative equilibria, and (self-) supervisory or other feedback signals -- which were necessary in other approaches. Its increased efficiency and biological compatibility do not trade off accuracy compared to state-of-the-art bio-plausible learning, but rather improve it. With up to five hidden layers and an added linear classifier, accuracies on MNIST, CIFAR-10, STL-10, and ImageNet, respectively reach 99.4%, 80.3%, 76.2%, and 27.3%. In conclusion, SoftHebb shows with a radically different approach from BP that Deep Learning over few layers may be plausible in the brain and increases the accuracy of bio-plausible machine learning. Code is available at https://github.com/NeuromorphicComputing/SoftHebb.

📄 PDF Abstract BibTeX arXiv:2209.11883

Code (1)

NeuromorphicComputing/SoftHebb 공식 구현 pytorch

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

2023-03-02 · CVPR 2023 1 · Yushun Tang, Ce Zhang, Heng Xu, Shuoshuo Chen 외

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We …

Test-time Adaptation

Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning

2025-10-16 · Shikuang Deng, Jiayuan Zhang, Yuhang Wu, Ting Chen 외 arxiv

Hebbian learning is a biological principle that intuitively describes how neurons adapt their connections through repeated stimuli. However, when applied to machine learning, it suffers serious issues due to the unconstr…

Image ClassificationImage ReconstructionContinual LearningTransfer Learning

A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics

2026-01-11 · Josh Li, Fow-sen Choa arxiv

Feedback-rich neural architectures can regenerate earlier representations and inject temporal context, making them a natural setting for strictly local synaptic plasticity. Existing literature raises doubt about whether …

Continual Learning

Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks

2021-07-04 · Thomas Miconi

Deep learning networks generally use non-biological learning methods. By contrast, networks based on more biologically plausible learning, such as Hebbian learning, show comparatively poor performance and difficulties of…

Deep LearningObject Recognition

Deep learning with asymmetric connections and Hebbian updates

2018-11-19 · Yali Amit

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers,…

Deep Learning