Results 41 to 50 of about 177,128 (280)

Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks

, 2021
Convolutional neural networks (CNNs) have been shown to achieve optimal approximation and estimation error rates (in minimax sense) in several function classes.
Oono, Kenta, Suzuki, Taiji
core  

From Wafers to Electrodes: Transferring Automatic Optical Inspection (AOI) for Multiscale Characterization of Smart Battery Manufacturing

Advanced Functional Materials, EarlyView.
Automat optical inspection (AOI) techniques in semiconductor fabrication can be leveraged in battery manufacturing, enabling scalable detection and analysis of electrode‐ and cell‐level imperfections through AI‐driven analytics and a digital‐twin framework.
Jianyu Li, Ertao Hu, Wei Wei, Feifei Shi
wiley   +1 more source

Revolutionizing Historical Manuscript Analysis: A Deep Learning Approach with Intelligent Feature Extraction for Script Classification

Acta Informatica Pragensia
The automated classification of historical document scripts holds profound implications for historians, providing unprecedented insights into the contexts of ancient manuscripts.
Merouane Boudraa, Akram Bennour, Tahar Mekhaznia, Abdulrahman Alqarafi, Rashiq Rafiq Marie, Mohammed Al-Sarem, Ayush Dogra   +6 more
doaj   +1 more source

A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification

, 2018
Convolutional Neural Networks (CNNs) have demonstrated their superiority in image classification, and evolutionary computation (EC) methods have recently been surging to automatically design the architectures of CNNs to save the tedious work of manually ...
A Krizhevsky, J Bruna, KV Price, Rainer Storn, TH Chan, Y LeCun, Y Lecun   +6 more
core   +1 more source

Multi‐Scale Interface Engineering of MXenes for Multifunctional Sensory Systems

Advanced Functional Materials, EarlyView.
MXenes, as two‐dimensional transition metal carbides and nitrides, demonstrate remarkable capabilities for multifunctional sensing applications. This review systematically examines multi‐scale interface engineering approaches that enhance sensing performance, enable diverse detection functionalities, and improve system‐level compatibility in MXene ...
Jiaying Liao, Sin‐Yi Pang, Jianhua Hao
wiley   +1 more source

Daily Prediction of the Arctic Sea Ice Concentration Using Reanalysis Data Based on a Convolutional LSTM Network

Journal of Marine Science and Engineering, 2021
To meet the increasing sailing demand of the Northeast Passage of the Arctic, a daily prediction model of sea ice concentration (SIC) based on the convolutional long short-term memory network (ConvLSTM) algorithm was proposed in this study.
Quanhong Liu, Ren Zhang, Yangjun Wang, Hengqian Yan, Mei Hong   +4 more
doaj   +1 more source

Simulating CRF with CNN for CNN

, 2019
Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired. In this paper, we propose a novel simple approach to CNN+CRF combination.
Gorelick, Lena, Veksler, Olga
openaire   +2 more sources

Texoskeletons: Developing the Fundamental Technologies for Creating Intelligent Soft Robotic Clothing With Integrated 1D Sensors and Actuators

Advanced Functional Materials, EarlyView.
ABSTRACT Traditional wearable exoskeletons rely on rigid structures, which limit comfort, flexibility, and everyday usability. This work introduces the fundamental technologies to create the first soft, lightweight, intelligent textile‐based exoskeletons (Texoskeletons) built using 1D sensors and actuators.
Amy Lukomiak, Rameesh Bulathsinghala, Jack Varga, Shuxin Meng, Kalana Marasinghe, Imaad Refai, Biyon Fernando, Amitkumar Patel, Chamika M. Halloluwa‐Arachchige, Carlos Oliveira, Arash M. Shahidi, Zahra Rahemtulla, Alexander Turner, Ziyun Ding, Bernard X. W. Liew, Andy Kerr, Ezio Preatoni, Theo Hughes‐Riley, Ishara Dharmasena, Pasindu Lugoda   +19 more
wiley   +1 more source

Performance comparison of single and ensemble CNN, LSTM and traditional ANN models for short‐term electricity load forecasting

The Journal of Engineering, 2022
The authors propose bagged and boosted convolutional neural networks (CNNs) and long short‐term memory (LSTM) networks, and compare their performance with the bagged and boosted traditional shallow artificial neural networks (ANNs) for short‐term ...
Arurun Kathirgamanathan, Afzal Patel, Ahmed S. Khwaja, Bala Venkatesh, Alagan Anpalagan   +4 more
doaj   +1 more source

Transfer of Learning in the Convolutional Neural Networks on Classifying Geometric Shapes Based on Local or Global Invariants

Frontiers in Computational Neuroscience, 2021
The convolutional neural networks (CNNs) are a powerful tool of image classification that has been widely adopted in applications of automated scene segmentation and identification. However, the mechanisms underlying CNN image classification remain to be
Yufeng Zheng, Jun Huang, Tianwen Chen, Yang Ou, Wu Zhou   +4 more
doaj   +1 more source