Results 81 to 90 of about 6,752,036 (307)

Mechanically Reprogrammed Coaxial Fibers for Multiphysics Transduction and Human‐Machine Interfaces

Advanced Science, EarlyView.
A continuously wet‐spun coaxial fiber is developed to combine stretchable conductivity, resistive sensing, and self‐powered triboelectric sensing in a single architecture. A mechanically reprogrammed dual‐network sheath stabilizes large deformation and improves signal reliability. These fibers can be woven into textile interfaces for multichannel touch
Xinyi Cao, Chao Ye, Shengjie Ling, Ming Li, Zhao Sha, Chun‐Hui Wang, Shuhua Peng   +6 more
wiley   +1 more source

Dictionary learning with structured noise

Neurocomputing, 2018
Abstract Recently, lots of dictionary learning methods have been proposed and successfully applied. However, many of them assume that the noise in data is drawn from Gaussian or Laplacian distribution and therefore they typically adopt the l 2 or l 1 norm to characterize these two kinds of noise, respectively.
Pan Zhou 0002, Cong Fang 0001, Zhouchen Lin, Chao Zhang 0001, Edward Y. Chang   +4 more
openaire   +2 more sources

Learning phase-invariant dictionaries [PDF]

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
In this paper, we present a novel algorithm to learn phase-invariant dictionaries, which can be used to efficiently approximate a variety of signals, such as audio signals or images. Our approach relies on finding a small number of generating atoms that can be used-along with their phase-shifts-to sparsely approximate a given signal.
Graeme Pope, Céline Aubel, Christoph Studer   +2 more
openaire   +1 more source

Robust Non-Negative Dictionary Learning

, 2014
Dictionary learning plays an important role in machine learning, where data vectors are modeled as a sparse linear combinations of basis factors (i.e., dictionary).
Pan, Qihe, Luo, Bin, Ding, Chris, Kong, Deguang, Deguang Kong, Qihe Pan, Bin Luo, Chris Ding   +7 more
core   +1 more source

Bridging Chemical Literature and Molecular Graphs: LLM‐Augmented Enantioselectivity Prediction for Iridium‐Catalyzed Asymmetric C–H Borylation

Advanced Science, EarlyView.
A machine‐learning framework for asymmetric C–H borylation bridges multi‐entity 3D molecular graphs and chemical literature. Atom‐resolved mechanistic annotations extracted by large language models augment three‐component graph encoding of catalyst, substrate, and product. The model predicts enantioselectivity with high accuracy on unseen scaffolds and
Zhe Wang, Baohua Zhang, Yi Isaac Yang, Yuan Yao, Yinwu Li   +4 more
wiley   +1 more source

An Analysis Dictionary Learning Algorithm under a Noisy Data Model with Orthogonality Constraint

The Scientific World Journal, 2014
Two common problems are often encountered in analysis dictionary learning (ADL) algorithms. The first one is that the original clean signals for learning the dictionary are assumed to be known, which otherwise need to be estimated from noisy measurements.
Ye Zhang, Tenglong Yu, Wenwu Wang
doaj   +1 more source

Solving Inverse Problems in Imaging via Deep Dictionary Learning

IEEE Access, 2019
In dictionary learning-based inversion, the dictionary and coefficients are learnt adaptively from the image during the inversion process; this is a shallow approach since one layer of the dictionary is learnt.
John Lewis D., Vanika Singhal, Angshul Majumdar   +2 more
doaj   +1 more source

SPD Data Dictionary Learning Based on Kernel Learning and Riemannian Metric

IEEE Access, 2020
The use of regional covariance descriptors to generate feature data represented by Symmetric Positive Definite (SPD) matrices from images or videos has become increasingly common in machine learning.
Rixin Zhuang, Zhengming Ma, Weijia Feng, Yuanping Lin   +3 more
doaj   +1 more source

Data‐Driven and Physics‐Informed Modeling Perspectives for Soft Manipulators: From SINDy to Hybrid Intelligence

Advanced Science, EarlyView.
This Perspective charts the modeling landscape for soft manipulators, spanning sparse system identification, neural dynamics, physics‐informed models and hybrid intelligence. We examine how physics, data, sensing, adaptation and control can assume complementary roles within this landscape, and provide a framework for selecting modeling approaches ...
Wenbo Hui, Yunyi Wang, Teng Zhang, Yang Chen, Min Pan   +4 more
wiley   +1 more source

SimCDL: A Simple Framework for Contrastive Dictionary Learning

Applied Sciences
In this paper, we propose a novel approach to the dictionary learning (DL) initialization problem, leveraging the SimCLR framework from deep learning in a self-supervised manner.
Denis C. Ilie-Ablachim, Bogdan Dumitrescu   +1 more
doaj   +1 more source