Results 111 to 120 of about 80,238 (283)
Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the vanilla gates in RNN (e.g., the input gate in LSTM) suffer from the problem of gate undertraining, which can be caused ...
Cheng, Zhanzhan +6 more
openaire +2 more sources
Electroactive Liquid Crystal Elastomers as Soft Actuators
Electroactive liquid crystal elastomers (eLCEs) can be actuated via electromechanical, electrochemical, or electrothermal effects. a) Electromechanical effects include Maxwell stress, electrostriction, and the electroclinic effect. b) Electrochemical effects arise from electrode redox reactions.
Yakui Deng, Min‐Hui Li
wiley +1 more source
Fe─NC porous oxygen reduction electrocatalysts are prepared employing a 2,4,6‐Triaminopyrimidine‐based porous organic polymer, a Mg2+ Lewis acid, and a low‐temperature cation exchange protocol. Using the polymer precursor achieves high pyrolysis yields and results in atomically dispersed FeNx sites. The resulting catalysts feature hierarchical porosity
Eliot Petitdemange +11 more
wiley +1 more source
A van der Waals optoelectronic synaptic device based on a ReS2/WSe2 heterostructure and oxygen‐treated h‐BN is presented, which enables both positive and negative PSCs through photocarrier polarity reversal. Bidirectional plasticity arises from gate‐tunable band bending and charge trapping‐induced quasi‐doping.
Hyejin Yoon +9 more
wiley +1 more source
Online Persian/Arabic Writer Identification using Gated Recurrent Unit Neural Networks
Conventional methods in writer identification mostly rely on hand-crafted features to represent the characteristics of different handwritten scripts.
Mahsa Aliakbarzadeh, Farbod Razzazi
doaj +1 more source
Minion Gated Recurrent Unit for Continual Learning
The increasing demand for continual learning in sequential data processing has led to progressively complex training methodologies and larger recurrent network architectures. Consequently, this has widened the knowledge gap between continual learning with recurrent neural networks (RNNs) and their ability to operate on devices with limited memory and ...
Zyarah, Abdullah M. +1 more
openaire +2 more sources
Spectrally Tunable 2D Material‐Based Infrared Photodetectors for Intelligent Optoelectronics
Intelligent optoelectronics through spectral engineering of 2D material‐based infrared photodetectors. Abstract The evolution of intelligent optoelectronic systems is driven by artificial intelligence (AI). However, their practical realization hinges on the ability to dynamically capture and process optical signals across a broad infrared (IR) spectrum.
Junheon Ha +18 more
wiley +1 more source
Integrative Approaches for DNA Sequence‐Controlled Functional Materials
DNA is emerging as a programmable building block for functional materials with applications in biomimicry, biochemical, and mechanical information processing. The integration of simulations, experiments, and machine learning is explored as a means to bridge DNA sequences with macroscopic material properties, highlighting current advances and providing ...
Aaron Gadzekpo +4 more
wiley +1 more source
Photo‐Switching Thermal and Lithium‐Ion Conductivity in Azobenzene Polymers
Light‐responsive azobenzene polymers control thermal and ionic transport simultaneously through structural transitions. UV illumination disrupts π–π stacking, converting crystalline trans states to amorphous cis configurations. Thermal conductivity drops from 0.45 to 0.15 W·m−1·K−1 while Li+ diffusivity increases 100 fold. This dual transport switching
Jaeuk Sung +7 more
wiley +1 more source
Anomalous Stiffening of a Conjugated Polymer During Electrochemical Oxidation
The electromechanical response of a thienothiophene‐based conjugated polymer with triethylene glycol side chains is investigated. Electrochemical nanoindentation and atomic force microscopy reveal a modest and reversible increase in elastic modulus at room temperature upon electrochemical oxidation.
Judith Pons i Tarrés +17 more
wiley +1 more source

