Consideration on liquid structure contributing to discrimination capability of Liquid State Machine
Consideration on liquid structure contributing to discrimination capability of Liquid State Machine
复制标题
DOI：
10.1587/nolta.11.36
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Tatsuro Sakaguchi;N. Wakamiya
中科院分区：
文献类型：
--
作者：
Tatsuro Sakaguchi;N. Wakamiya
液态机（Liquid State Machine，LSM）是一种水库计算模型，由于其通用的计算能力，其应用和改进一直受到研究者的关注。与此同时，测量技术的发展揭示了脑网络中存在的无标度、小世界、模块化等特殊结构，这些结构对认知、记忆等高阶脑功能有重要作用。在本文中，我们应用各种网络模型的递归神经网络的最小二乘模型和研究之间的关系的结构特性和准确性的歧视。结果表明，模块化的递归神经网络提高了LSM的歧视能力。
Liquid State Machine (LSM) is one of reservoir computing models and due to universal computing capability its application and improvement attract researchers. Meanwhile development of measurement technology reveals the existence of specific structure in brain networks, such as scale-free, small-world, and modular properties, which contribute to higherorder brain functions such as cognition and memory. In this paper, we apply various network models to a recurrent neural network of an LSM and investigate the relationship between structural properties and accuracy of discrimination. Results suggest that modularity of a recurrent neural network enhances discrimination capability of LSM.