[TuP-G] Poster Session 1

[TuP-G-6] Integrated Photonic Reservoir Computing with Tunable Memory Capacity

Yihang Lai¹, Zhiwei Yang¹, Qi Chen¹, Zili Cai¹, ○Tian Zhang¹, Jian Dai¹, Kun Xu¹ (1. State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telcommunications (China))

Keywords:

Optical neural networks and reservoir computing,Programmable,reconfigurable photonics

We propose a novel integrated reservoir computing scheme with dynamically adjustable short-term memory capacity, ranging from 0-20. Our scheme can efficiently complete NARMA time series prediction tasks while meeting different memory capacity requirements