Results 111 to 120 of about 1,451,519 (348)

Optical frontend for a convolutional neural network

Applied Optics, 2019
The parallelism of optics and the miniaturization of optical components using nanophotonic structures, such as metasurfaces present a compelling alternative to electronic implementations of convolutional neural networks. The lack of a low-power optical nonlinearity, however, requires slow and energy-inefficient conversions between the electronic and ...
Shane Colburn, Yi Chu, Eli Shilzerman, Arka Majumdar   +3 more
openaire   +3 more sources

Bioinspired Adaptive Sensors: A Review on Current Developments in Theory and Application

Advanced Materials, EarlyView.
This review comprehensively summarizes the recent progress in the design and fabrication of sensory‐adaptation‐inspired devices and highlights their valuable applications in electronic skin, wearable electronics, and machine vision. The existing challenges and future directions are addressed in aspects such as device performance optimization ...
Guodong Gong, You Zhou, Qingxiu Li, Wenyu Zhao, Sunyingyue Geng, Hangfei Li, Yan‐Bing Leng, Shirui Zhu, Guanglong Ding, Yongbiao Zhai, Ziyu Lv, Ye Zhou, Su‐Ting Han   +12 more
wiley   +1 more source

Convolutional Neural Networks: A Survey

Computers, 2023
Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of AI that have emerged as a powerful tool for various tasks including image recognition, speech recognition, natural language processing (NLP), and even in the field of ...
openaire   +2 more sources

AI‐Driven Defect Engineering for Advanced Thermoelectric Materials

Advanced Materials, EarlyView.
This review presents how AI accelerates the design of defect‐tuned thermoelectric materials. By integrating machine learning with high‐throughput data and physics‐informed representations, it enables efficient prediction of thermoelectric performance from complex defect landscapes.
Chu‐Liang Fu, Mouyang Cheng, Nguyen Tuan Hung, Eunbi Rha, Zhantao Chen, Ryotaro Okabe, Denisse Córdova Carrizales, Manasi Mandal, Yongqiang Cheng, Mingda Li   +9 more
wiley   +1 more source

Hardware Implementation of On‐Chip Hebbian Learning Through Integrated Neuromorphic Architecture

Advanced Materials, EarlyView.
This work presents a neuromorphic hardware platform that integrates presynaptic transistors, threshold switching neurons, and adaptive feedback synapses. The architecture enables on‐chip Hebbian learning through correlation‐based weight updates without external training circuits.
Seonkwon Kim, Seongil Im, In Cheol Kwak, Jungwha Lee, Dong Gue Roe, Hyunsu Ju, Jeong Ho Cho   +6 more
wiley   +1 more source

Spatial Coordination Structure‐Driven Enzyme‐Like Selectivity in Single‐Atom Nanozymes

Advanced Materials, EarlyView.
Sun et al. reviews recent progress in enhancing the enzyme‐like catalytic selectivity of SAzymes through the rational design of their spatial coordination structures. They emphasize the structure‐activity relationships of various attributes of these coordination structures in promoting selective catalytic behavior, the strategic design of coordination ...
Qijun Sun, Si Liu, Ziping Li, Peiji Deng, Na Niu, Ligang Chen, Kang Liang   +6 more
wiley   +1 more source

Application of deep learning for division of petroleum reservoirs

MATEC Web of Conferences, 2018
Traditional methods of dividing petroleum reservoirs are inefficient, and the accuracy of onehidden-layer BP neural network is not ideal when applied to dividing reservoirs.
Qin Yaqiong, Ye Zhaohui, Zhang Conghui
doaj   +1 more source

Object Detection and Feature Base Learning with Sparse Convolutional Neural Networks [PDF]

, 2006
Alexander Gepperth
openalex   +1 more source

Fibrous Pressure Sensor with Unique Resistance Increase under Partial Compression: Coaxial Wet‐Spun TiO2/Graphene/Thermoplastic Polyurethane Multi‐Wall Multifunctional Fiber

Advanced Materials, EarlyView.
TGTMW fibers are designed to show a sharp resistance increase under pressure, as the multi‐wall structure in the transition region between compressed and uncompressed areas bends and forms microcracks. This design breaks the physical sensitivity limit of conventional fiber‐shaped pressure sensors, which usually show resistance reduction under pressure ...
Ziwei Chen, Dandan Xie, Kanae Kojima, Chunxia Gao, Jian Shi, Jian Xing, Hideaki Morikawa, Chunhong Zhu   +7 more
wiley   +1 more source

A hybrid approach of deep learning to forecast financial performance: from unsupervised to supervised

Systems Science & Control Engineering
The financial performance of a listed company is a common concern for shareholders, creditors, employees, securities analysts, and the government. Measuring and forecasting financial performance informs stakeholders about a company's overall well-being ...
Jiadong Teng
doaj   +1 more source