Analysis and fully memristor-based reservoir computing for temporal data classification.
Ankur Singh, Sanghyeon Choi, Gunuk Wang, Maryaradhiya Daimari, Byung-Geun Lee
Author Information
Ankur Singh: School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea. Electronic address: ankursingh@gm.gist.ac.kr.
Sanghyeon Choi: Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, 93106, USA. Electronic address: chl299@ucsb.edu.
Gunuk Wang: KU-KIST Graduate School of Converging Science and Technology, and Department of Integrative Energy Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea. Electronic address: gunukwang@korea.ac.kr.
Maryaradhiya Daimari: School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea. Electronic address: maryaradhiya@gm.gist.ac.kr.
Byung-Geun Lee: School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea. Electronic address: bglee@gist.ac.kr.
Reservoir computing (RC) offers a neuromorphic framework that is particularly effective for processing spatiotemporal signals. Known for its temporal processing prowess, RC significantly lowers training costs compared to conventional recurrent neural networks. A key component in its hardware deployment is the ability to generate dynamic reservoir states. Our research introduces a novel dual-memory RC system, integrating a short-term memory via a WO-based memristor, capable of achieving 16 distinct states encoded over 4 bits, and a long-term memory component using a TiO-based memristor within the readout layer. We thoroughly examine both memristor types and leverage the RC system to process temporal data sets. The performance of the proposed RC system is validated through two benchmark tasks: isolated spoken digit recognition and with only a fraction of complete samples forecasting the Mackey-Glass (MG) time series prediction. The system delivered an impressive 98.84% accuracy in speech digit recognition and sustained a low normalized root mean square error (NRMSE) of 0.036 in the time series prediction task, underscoring its capability. This study illuminates the adeptness of memristor-based RC systems in managing intricate temporal challenges, laying the groundwork for further innovations in neuromorphic computing.
