.png){kind=icon}
返回
Efficient optical reservoir computing for parallel data processing
.png){kind=icon}
PRE
AI
DOI：10.1364/OL.464288.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose and experimentally demonstrate an optical reservoir computing system in free space, using second-harmonic generation for nonlinear kernel functions and a scattering medium to enhance reservoir nodes interconnection. We test it for one-step and multi-step predication of Mackey-Glass time series with different input-mapping methods on a spatial light modulator. For one-step prediction, we achieve 1.8 x 10(-3) normalized mean squared error (NMSE). For the multi-step prediction, we explore two different mapping methods: linear-combination and concatenation, achieving 16-step prediction with NMSE as low as 3.5 x 10(-4). Robust and superior for multi-step prediction, our approach and design have potential for parallel data processing tasks such as video prediction, speech translation, and so on. (C) 2022 Optica Publishing Group
Keyword:
RECOGNITION
期刊
IF:
3.3
论文数:
4.0W
被引数:
7.6W
机构
引用论文
A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏First-Principle Protocol for Calculating Ionization Energies and Redox Potentials of Solvated Molecules and Ions: Theory and Application to Aqueous Phenol and Phenolate计算溶剂化分子和离子的电离能和氧化还原电位的第一原理协议: 理论和对苯酚和酚盐水溶液的应用
OAAI
OAAI分享收藏Reinforcement learning in a large-scale photonic recurrent neural network大规模光子递归神经网络中的强化学习OPTICAOAAI
OPTICAIF8.5
OAAI分享收藏
查看更多内容