Model-Size Reduction for Reservoir Computing by Concatenating Internal States Through Time
Institute of Industrial Science, The University of Tokyo（东京大学工业科学研究所）；NEC Corporation（NEC公司）；Interdisciplinary Graduate School of Engineering Sciences, Kyushu University（九州大学工学研究院跨学科工学研究科）；International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo Institutes for Advanced Study, The University of Tokyo（东京大学高等研究院国际神经智能研究中心（WPI-IRCN））
Yusuke Sakemi, Kai Morino, Timothée Leleu, Kazuyuki Aihara
Reservoir computing (RC) is a machine learning algorithm that can learn complex time series from data very rapidly based on the use of high-dimensional dynamical systems, such as random networks of neurons, called "reservoirs." To implement RC in edge computing, it is highly important to reduce the amount of computational resources that RC requires. In this study, we propose methods that reduce the size of the reservoir by inputting the past or drifting states of the reservoir to the output layer at the current time step. These proposed methods are analyzed based on information processing capacity, which is a performance measure of RC proposed by Dambre et al. (2012). In addition, we evaluate the effectiveness of the proposed methods on time-series prediction tasks: the generalized Henon-map and NARMA. On these tasks, we found that the proposed methods were able to reduce the size of the reservoir up to one tenth without a substantial increase in regression error. Because the applications of the proposed methods are not limited to a specific network structure of the reservoir, the proposed methods could further improve the energy efficiency of RC-based systems, such as FPGAs and photonic systems.
Reservoir Computing meets Recurrent Kernels and Structured Transforms
Ecole Normale Supérieure（巴黎高等师范学院）；Université PSL（巴黎文理研究大学）；CNRS（法国国家科学研究中心）；Sorbonne Université（索邦大学）；Université de Paris（巴黎大学）；Collège de France（法兰西公学院）；LightOn（LightOn公司）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Prediction of Unobserved Bifurcation by Unsupervised Extraction of Slowly Time-Varying System Parameter Dynamics from Time Series Using Reservoir Computing
Faculty of Health Data science, Juntendo University（顺天堂大学健康数据科学学部）；The School of Systems Information Science, Future University Hakodate（函馆未来大学系统信息科学学院）
Improving the Performance of Echo State Networks Through State Feedback
Wyant College of Optical Sciences, University of Arizona（亚利桑那大学怀恩特光学科学学院）；School of Electrical Engineering and Telecommunications, University of New South Wales（新南威尔士大学电气工程与电信学院）
University of York（约克大学）；School of Physics, Engineering and Technology, University of York（约克大学物理、工程与技术学院）；Department of Chemistry, University of York（约克大学化学系）；Department of Computer Science, University of York（约克大学计算机科学系）
What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity
University Paris Saclay, INRAE, AgroParisTech, MICALIS Institute（巴黎萨克雷大学、法国国家农业研究院、阿格罗巴黎科技大学、MICALIS研究所）；LaBRI, Bordeaux INP, CNRS, UMR 5800, France（LaBRI、波尔多INP、CNRS、UMR 5800、法国）
