研究人员开发了一种通过混合平衡传播（Equilibrium Propagation）与Ising Machines来训练基于能量的神经网络的新方法。该方法旨在通过修改神经网络状态的物理动力学来克服基于GPU的传统训练的能量需求并提高收敛性。新框架在各种数据集上展示了与反向传播（backpropagation）相当的性能，并为更节能的AI硬件指明了方向。 AI
影响 该研究通过利用物理计算原理，为更节能的AI硬件提供了一条潜在的途径。
排序理由 该集群包含两篇arXiv论文，详细介绍了一种新颖的神经网络训练研究方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.09112v1 Announce Type: cross Abstract: The rapid evolution of artificial intelligence has led to substantial advances in deep neural networks. Nonetheless, conventional GPU-based training remains highly energy-demanding, motivating the exploration of physical dynamics …
arXiv:2606.09117v1 Announce Type: cross Abstract: While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by h…