paper-with-me

Papers

Mono-Forward: Backpropagation-Free Algorithm for Efficient Neural Network Training Harnessing Local Errors

2025-01-16 · James Gong, Bruce Li, Waleed Abdulla

Backpropagation is the standard method for achieving state-of-the-art accuracy in neural network training, but it often imposes high memory costs and lacks biological plausibility. In this paper, we introduce the Mono-Forward algorithm, a purely local layerwise learning method inspired by Hinton's Forward-Forward framework. Unlike backpropagation, Mono-Forward optimizes each layer solely with locally available information, eliminating the reliance on global error signals. We evaluated Mono-Forward on multi-layer perceptrons and convolutional neural networks across multiple benchmarks, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. The test results show that Mono-Forward consistently matches or surpasses the accuracy of backpropagation across all tasks, with significantly reduced and more even memory usage, better parallelizability, and a comparable convergence rate.

📄 PDF Abstract BibTeX arXiv:2501.09238

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient Neural Network

Similar Papers 제목 키워드 기반

Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms

2025-11-02 · Przemysław Spyra, Witold Dzwinel arxiv

The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpr…

Hyperparameter Optimization

Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm

2025-02-19 · Mohammadnavid Ghader, Saeed Reza Kheradpisheh, Bahar Farahani, Mahmood Fazlali

Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs with traditional backpr…

Computational Efficiency

Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training

2025-09-23 · Przemysław Spyra arxiv

The rising computational and energy demands of deep neural networks (DNNs), driven largely by backpropagation (BP), challenge sustainable AI development. This paper rigorously investigates three BP-free training methods:…

Local learning for stable backpropagation-free neural network training towards physical learning

2026-03-25 · Yaqi Guo, Fabian Braun, Bastiaan Ketelaar, Stephanie Tan 외 arxiv

While backpropagation and automatic differentiation have driven deep learning's success, the physical limits of chip manufacturing and rising environmental costs of deep learning motivate alternative learning paradigms s…

FedFwd: Federated Learning without Backpropagation

2023-09-03 · Seonghwan Park, Dahun Shin, Jinseok Chung, Namhoon Lee

In federated learning (FL), clients with limited resources can disrupt the training efficiency. A potential solution to this problem is to leverage a new learning procedure that does not rely on backpropagation (BP). We …

Federated Learning