Optimizing reservoir connectivity: A path to high-performance liquid state machines
Authors:
- Seungmin OhSOSeungmin Oh
- Unhyeon KangUKUnhyeon Kang
- Jaewook KimJKJaewook Kim
- Jingyeong HwangJHJingyeong Hwang
- Jiin BangJBJiin Bang
- Kyungmin LeeKLKyungmin Lee
- Younghyun LeeYLYounghyun Lee
- Jongkil ParkJPJongkil Park
- Seongsik ParkSPSeongsik Park
- Hyun Jae JangHJHyun Jae Jang
- Changyoung KimCKChangyoung Kim
- Suyoun LeeSLSuyoun Lee
- 7 November 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 663
Abstract
No abstract availableFunding Information
- Ministry of Science and ICT, South Korea (GTL24041\u2013000)
- National Research Council of Science and Technology
- Korea Institute of Science and Technology (2E33560)
This publication has 26 references indexed in Scilit:
- Analysis and fully memristor-based reservoir computing for temporal data classificationNeural Networks, 2024
- Recent advances in physical reservoir computing: A reviewNeural Networks, 2019
- Deep learningNature, 2015
- Information processing using a single dynamical node as complex systemNature Communications, 2011
- Edge of chaos and prediction of computational performance for neural circuit modelsNeural Networks, 2007
- An experimental unification of reservoir computing methodsNeural Networks, 2007
- Interneurons of the neocortical inhibitory systemNature Reviews Neuroscience, 2004
- Fluctuating synaptic conductances recreate in vivo-like activity in neocortical neuronsNeuroscience, 2001
- A practical method for calculating largest Lyapunov exponents from small data setsPhysica D: Nonlinear Phenomena, 1993
- Determining Lyapunov exponents from a time seriesPhysica D: Nonlinear Phenomena, 1985