发表机构
Satenlight（Satenlight）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种基于输入依赖随机权重网络的通用模型，通过二次多项式权重函数和协方差核实现无需传统训练的神经形态启发计算，数值模拟验证了相关性对系统响应的影响。
AI 中文摘要
近年来，学术界和工业界都致力于开发受生物神经系统分布式、自适应和事件驱动特性启发的计算架构，旨在降低与传统训练方法相关的计算成本[1]。然而，一个主要挑战是新兴计算系统和硬件缺乏通用模型和设计指南。这项工作引入了一种基于输入依赖的随机权重网络（称为基底）的通用模型。基底权重通过输入触发的随机更新演化，权重系数之间的相关性由矩阵值协方差核描述。所提出的框架使用二次多项式权重函数实现，其中输入幅度控制随机扰动的强度，而基底依赖的距离决定相关结构。数值模拟表明，随机权重演化中的相关性显著影响系统响应，这暗示了一种无需传统权重训练的神经形态启发计算的潜在机制。本工作的目标是提供该模型的通用表述，并确定其主要性质和特征。1 H. Jaeger，迈向包含数字、神经形态和非常规计算的广义理论，Neuromorphic Comput. Eng.，第1卷，第1期，第012002页，2021年9月。
英文摘要
In recent years, both academia and industry have focused on the development of computational architectures inspired by the distributed, adaptive, and event-driven characteristics of biological neural systems, with the aim of reducing the computational cost associated with conventional training approaches [1]. However, a major challenge is the lack of general models and design guidelines for emerging computational systems and hardware. This work introduces a general model based on an input-dependent stochastic weight network, referred to as a substrate. The substrate weights evolve through input-triggered stochastic updates, with correlations between weight coefficients described by a matrix-valued covariance kernel. The proposed framework is implemented using quadratic polynomial weight functions, where the input amplitude controls the magnitude of the stochastic perturbation and a substrate-dependent distance determines the correlation structure. Numerical simulations show that correlations in the stochastic weight evolution significantly affect the system response, suggesting a potential mechanism for neuromorphic-inspired computation without conventional weight training. The aim of this work is to provide a general formulation of the model and identify its main properties and characteristics. 1 H. Jaeger, Towards a generalized theory comprising digital, neuromorphic and unconventional computing, Neuromorphic Comput. Eng., vol. 1, no. 1, p. 012002, Sep. 2021
Comments15 pages, 5 figures
