Physical reservoir computing with emerging electronics
Physical reservoir computing is a form of neuromorphic computing that harvests the dynamic
properties of materials for high-efficiency computing. A wide range of physical systems can …
properties of materials for high-efficiency computing. A wide range of physical systems can …
Photonic neuromorphic technologies in optical communications
A Argyris - Nanophotonics, 2022 - degruyter.com
Abstract Machine learning (ML) and neuromorphic computing have been enforcing problem-
solving in many applications. Such approaches found fertile ground in optical …
solving in many applications. Such approaches found fertile ground in optical …
Attention-based CNN and Bi-LSTM model based on TF-IDF and glove word embedding for sentiment analysis
M Kamyab, G Liu, M Adjeisah - Applied Sciences, 2021 - mdpi.com
Sentiment analysis (SA) detects people's opinions from text engaging natural language
processing (NLP) techniques. Recent research has shown that deep learning models, ie …
processing (NLP) techniques. Recent research has shown that deep learning models, ie …
Blinking coupling enhances network synchronization
This paper studies the synchronization of a network with linear diffusive coupling, which
blinks between the variables periodically. The synchronization of the blinking network in the …
blinks between the variables periodically. The synchronization of the blinking network in the …
Generative complex networks within a dynamic memristor with intrinsic variability
Y Guo, W Duan, X Liu, X Wang, L Wang… - Nature …, 2023 - nature.com
Artificial neural networks (ANNs) have gained considerable momentum in the past decade.
Although at first the main task of the ANN paradigm was to tune the connection weights in …
Although at first the main task of the ANN paradigm was to tune the connection weights in …
An all-in-one multifunctional touch sensor with carbon-based gradient resistance elements
C Wei, W Lin, S Liang, M Chen, Y Zheng, X Liao… - Nano-micro letters, 2022 - Springer
Highlights Carbon-based gradient resistance element structure is proposed for the
construction of multifunctional touch sensor, which will promote wide detection and …
construction of multifunctional touch sensor, which will promote wide detection and …
High-speed photonic neuromorphic computing using recurrent optical spectrum slicing neural networks
Neuromorphic computing using photonic hardware is a promising route towards ultrafast
processing while maintaining low power consumption. Here we present and numerically …
processing while maintaining low power consumption. Here we present and numerically …
Large-scale photonic natural language processing
Modern machine-learning applications require huge artificial networks demanding
computational power and memory. Light-based platforms promise ultrafast and energy …
computational power and memory. Light-based platforms promise ultrafast and energy …
Connecting reservoir computing with statistical forecasting and deep neural networks
L Jaurigue, K Lüdge - Nature Communications, 2022 - nature.com
Standfirst Among the existing machine learning frameworks, reservoir computing
demonstrates fast and low-cost training, and its suitability for implementation in various …
demonstrates fast and low-cost training, and its suitability for implementation in various …
[PDF][PDF] 片上集成光学神经网络综述(特邀)
符庭钊, 孙润, 黄禹尧, 张检发, 杨四刚, 朱志宏… - 中国激光, 2024 - researching.cn
摘要光学神经网络是区别于冯· 诺依曼计算架构的一种高性能新型计算范式, 具有低延时,
低功耗, 大带宽以及并行信号处理等优势. 片上集成是光学神经网络微型化发展的一种典型方式 …
低功耗, 大带宽以及并行信号处理等优势. 片上集成是光学神经网络微型化发展的一种典型方式 …