Two-Step FORCE Learning Algorithm for Fast Convergence in Reservoir Computing

被引：6

作者：

Tamura, Hiroto ^{[1
,2
]}

Tanaka, Gouhei ^{[1
,2
]}

机构：

[1] Univ Tokyo, Grad Sch Engn, Tokyo 1138656, Japan

[2] Univ Tokyo, Int Res Ctr Neurointelligence, Tokyo 1130033, Japan

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT II | 2020年 / 12397卷

关键词：

Reservoir computing; FORCE learning; Edge computing; Nonlinear time series generation;

D O I：

10.1007/978-3-030-61616-8_37

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Reservoir computing devices are promising as energy-efficient machine learning hardware for real-time information processing. However, some online algorithms for reservoir computing are not simple enough for hardware implementation. In this study, we focus on the first order reduced and controlled error (FORCE) algorithm for online learning with reservoir computing models. We propose a two-step FORCE algorithm by simplifying the operations in the FORCE algorithm, which can reduce necessary memories. We analytically and numerically show that the proposed algorithm can converge faster than the original FORCE algorithm.

引用

页码：459 / 469

页数：11