密集联想记忆的自由能景观
Free energy landscape of Dense Associative Memory
浏览论文内容
中文总结 AI 辅助
该研究利用大偏差理论求解密集联想记忆的自由能泛函,通过重现Hopfield模型结果说明方法,推导有限模式下相关自由能泛函,评估基态能量,揭示记忆检索与初始状态关系并给出LSE模型全检索阈值,为分析联想记忆架构提供系统程序。
中文摘要 AI 辅助
利用大偏差理论,我们求解并得到了包括密集联想记忆在内的一大类联想记忆的自由能泛函的一般表达式。我们通过重现Hopfield模型的经典结果来说明该方法。对于有限数量的模式,我们推导了具有多项式相互作用和对数和指数(LSE)激活的密集联想记忆的温度相关自由能泛函。我们还在广泛的极限下评估了这些系统的无序平均基态能量。我们的分析框架揭示了记忆检索如何依赖于高阶密集网络中的初始状态,并给出了LSE模型的精确全检索阈值。该方法为分析联想记忆中不同复杂架构提供了系统程序。
英文摘要
Using large deviations theory, we solve and obtain a general expression for the free energy functional for a broad class of associative memories, including dense associative memories. We illustrate the method by reproducing classical results for the Hopfield model. For a finite number of patterns, we derive the temperature-dependent free energy functional for dense associative memories featuring polynomial interactions and Log-Sum-Exponential (LSE) activation. We also evaluate the disorder-averaged ground-state energy of these systems in the extensive limit. Our analytical framework reveals how memory retrieval depends on the initial state in higher-order dense networks, and gives the exact full-retrieval threshold for the LSE model. This method provides a systematic procedure for analyzing diverse, complex architectures in associative memory.
发表机构
- School of Physical Sciences, National Institute of Science Education and Research(物理科学学院,国家科学教育与研究机构)
- Homi Bhabha National Institute(霍米·巴布哈国家研究所)
机构由 AI 辅助整理,请以论文原文为准。