English(EN) Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

平衡传播可扩展至在ImageNet上训练大型预测编码网络

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-02 12:52

研究人员开发了一种使用平衡传播（EP）这一基于物理学的框架来训练预测编码网络（PCNs）的新方法。这种新颖的方法成功地将EP和PCNs扩展到在完整的ImageNet数据集上训练一个10层卷积网络。该训练网络的top-5分类错误率为13.23%，接近传统反向传播方法的12.2%错误率。 AI

影响展示了一种可扩展的能量模型训练方法，可能为大规模AI研究开辟新途径。

排序理由该集群包含一篇学术论文，详细介绍了一种训练特定类型神经网络的新方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Tugdual Kerjan, Rasmus H{\o}ier, Benjamin Scellier · 2026-06-03 04:00

Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

arXiv:2606.03584v1 Announce Type: new Abstract: Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfield networks, nonlinear resistive networks and coupled phase oscillators. However,…
arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Benjamin Scellier · 2026-06-02 12:52

使用平衡传播在 ImageNet 上训练预测编码网络

Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfield networks, nonlinear resistive networks and coupled phase oscillators. However, EP's practical applications have so far remaine…