基于阈值线性网络的联想记忆系统
Associative Memory System via Threshold Linear Networks
AI总结:
本文提出一种新型在线自关联记忆系统,支持序列记忆形成并提供鲁棒记忆检索的理论保证,通过阈值线性网络与编码器、解码器和控制器结合实现模式重构。
摘要:
人类在随机环境中学习和形成记忆。自关联记忆系统通过存储模式并在后续从损坏版本中恢复它们来建模这些过程。在此工作中,我们提出了一种新的在线自关联记忆系统。与现有工作不同,我们的系统支持序列记忆形成,并通过吸引域分析提供正式的鲁棒记忆检索保证。我们使用阈值线性网络作为潜在空间动力学,结合编码器、解码器和控制器。我们在模拟中展示该记忆系统能够从损坏输入中成功重构模式。
英文摘要:
Humans learn and form memories in stochastic environments. Auto-associative memory systems model these processes by storing patterns and later recovering them from corrupted versions. Here, memories are learned by associating each pattern with an attractor in a latent space. After learning, when (possibly corrupted) patterns are presented to the system, latent dynamics facilitate retrieval of the appropriate uncorrupted pattern. In this work, we propose a novel online auto-associative memory system. In contrast to existing works, our system supports sequential memory formation and provides formal guarantees of robust memory retrieval via region-of-attraction analysis. We use a threshold-linear network as latent space dynamics in combination with an encoder, decoder, and controller. We show in simulation that the memory system successfully reconstructs patterns from corrupted inputs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。