用现代方法解析联想记忆，连接主流AI模型与理论框架。
Modern Methods in Associative Memory
- 基于新理论框架重构联想记忆模型，统一理解其计算机制。
- 揭示联想记忆与Transformer、扩散模型的深层关联。
- 适合想深入理解神经网络理论基础的研究者和实践者。
联想记忆（如著名的霍普菲尔德网络）是描述全连接神经网络的优雅模型，其核心功能是存储与检索信息。近年来，由于关于其信息存储能力的新理论成果，以及与当前领先AI架构（如Transformer和扩散模型）的关联性研究，该领域重获关注。这些联系为通过联想记忆的理论视角解释传统AI网络的计算过程提供了可能。此外，新的拉格朗日形式化方法使得设计强大的分布式模型成为可能，这些模型能学习有用表示并启发新型架构的设计。本教程提供了一种易懂的入门介绍，重点阐述该领域的现代语言与方法，包含实用的数学推导和代码笔记。
原文摘要 · Abstract (English)
Associative Memories like the famous Hopfield Networks are elegant models for describing fully recurrent neural networks whose fundamental job is to store and retrieve information. In the past few years they experienced a surge of interest due to novel theoretical results pertaining to their information storage capabilities, and their relationship with SOTA AI architectures, such as Transformers and Diffusion Models. These connections open up possibilities for interpreting the computation of traditional AI networks through the theoretical lens of Associative Memories. Additionally, novel Lagrangian formulations of these networks make it possible to design powerful distributed models that learn useful representations and inform the design of novel architectures. This tutorial provides an approachable introduction to Associative Memories, emphasizing the modern language and methods used in this area of research, with practical hands-on mathematical derivations and coding notebooks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。