吸引子神经网络中的向量符号有限状态机
Vector Symbolic Finite State Machines in Attractor Neural Networks
AI总结:
本文提出构造规则使Hopfield吸引子网络能实现任意有限状态机,并证明其容量随网络规模线性或二次增长,且对噪声权重鲁棒,为生物神经网络中的分布式计算原语提供了可能路径。
摘要:
Hopfield吸引子网络是人类记忆的鲁棒分布式模型,但缺乏一种通用机制来响应输入实现状态依赖的吸引子转换。我们提出构造规则,使吸引子网络能够实现任意有限状态机(FSM),其中状态和刺激由高维随机向量表示,所有状态转换均由吸引子网络的动力学完成。数值模拟表明,该模型的容量(以可实现的FSM最大规模衡量)对于稠密双极状态向量与吸引子网络规模呈线性关系,对于稀疏二值状态向量则近似呈二次关系。我们证明该模型对不精确和含噪声的权重具有鲁棒性,因此是使用高密度但不可靠器件实现的主要候选方案。通过赋予吸引子网络模拟任意FSM的能力,我们提出了一条可能的路径,使FSM能够作为生物神经网络中的分布式计算原语存在。
英文摘要:
Hopfield attractor networks are robust distributed models of human memory, but lack a general mechanism for effecting state-dependent attractor transitions in response to input. We propose construction rules such that an attractor network may implement an arbitrary finite state machine (FSM), where states and stimuli are represented by high-dimensional random vectors, and all state transitions are enacted by the attractor network's dynamics. Numerical simulations show the capacity of the model, in terms of the maximum size of implementable FSM, to be linear in the size of the attractor network for dense bipolar state vectors, and approximately quadratic for sparse binary state vectors. We show that the model is robust to imprecise and noisy weights, and so a prime candidate for implementation with high-density but unreliable devices. By endowing attractor networks with the ability to emulate arbitrary FSMs, we propose a plausible path by which FSMs could exist as a distributed computational primitive in biological neural networks.
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。