Results 231 to 240 of about 3,893 (298)

A Review of Modified/Consistent Couple Stress and Strain Gradient Theories for Analyzing Static and Dynamic Behaviors of Functionally Graded Microscale Plates and Shells. [PDF]

Materials (Basel)
Wu CP, Chang TY.
europepmc   +1 more source

Review of Memristors for In‐Memory Computing and Spiking Neural Networks

Advanced Intelligent Systems, EarlyView.
Memristors uniquely enable energy‐efficient, brain‐inspired computing by acting as both memory and synaptic elements. This review highlights their physical mechanisms, integration in crossbar arrays, and role in spiking neural networks. Key challenges, including variability, relaxation, and stochastic switching, are discussed, alongside emerging ...
Mostafa Shooshtari, Teresa Serrano‐Gotarredona, Bernabé Linares‐Barranco   +2 more
wiley   +1 more source

Fast and Fourier features for transfer learning of interatomic potentials. [PDF]

NPJ Comput Mater
Novelli P, Meanti G, Buigues PJ, Rosasco L, Parrinello M, Pontil M, Bonati L.   +6 more
europepmc   +1 more source

Robust Dysarthric Speech Recognition with GAN Enhancement and LLM Correction

Advanced Intelligent Systems, EarlyView.
This study tackles dysarthric speech recognition by combining generative adversarial network (GAN)‐generated synthetic data with large language model (LLM)‐based error correction. The approach integrates three key elements: an improved CycleGAN to generate synthetic dysarthric speech for data augmentation, a multimodal automatic speech recognition core
Yibo He, Kah Phooi Seng, Chee Shen Lim, Li Minn Ang   +3 more
wiley   +1 more source

Lower Bounds on the Noiseless Worst-Case Complexity of Efficient Global Optimization. [PDF]

J Optim Theory Appl
Xu W, Jiang Y, Maddalena ET, Jones CN.
europepmc   +1 more source

Data‐Driven Design of Bimodal Networked Dielectric Elastomers for High‐Performance Artificial Muscles

Advanced Intelligent Systems, EarlyView.
A data‐efficient artificial intelligence‐assisted framework, which integrates experimental data with machine learning, is developed for the design of bimodal networked dielectric elastomers (DEs) as advanced artificial muscles. It adopts neural networks to predict DEs’ mechanical properties and support vector machines to classify electromechanical ...
Ofoq Normahmedov, Hanzhi Ma, Junbo Peng, Huifeng Dong, Jiangshan Zhuo, Mengke Shi, Lvting Wang, Shengchao Jiang, Ye Shi   +8 more
wiley   +1 more source

CABNas-nir: A near-infrared classification for urban pipe network sludge on the fusion algorithm of NAS framework and active learning. [PDF]

PLoS One
Yang Y, Fu L, Wei Q, Feng Y, Zhu L, Dai Y, Xiao W, Fan T, Jin X.   +8 more
europepmc   +1 more source

RanBALL: An Ensemble Machine Learning Framework for Accurate Subtype Identification of Pediatric B‐Cell Acute Lymphoblastic Leukemia

Advanced Intelligent Systems, EarlyView.
Here, we present RanBALL, an ensemble random projection‐based model for accurate and cost‐effective identification of B‐cell acute lymphoblastic leukemia subtypes is presented. By preserving patient‐to‐patient distance after dimension reduction by random projection and ensemble learning, RanBALL can facilitate the discovery of B‐ALL subtype‐specific ...
Lusheng Li, Hanyu Xiao, Xinchao Wu, Zhenya Tang, Joseph D. Khoury, Jieqiong Wang, Shibiao Wan   +6 more
wiley   +1 more source

Kinetically Consistent Coarse Graining Using Kernel-Based Extended Dynamic Mode Decomposition. [PDF]

J Chem Theory Comput
Nateghi V, Nüske F.
europepmc   +1 more source

Metalearning‐Driven Inverse Optimization for Precision Microstructure Fabrication in Digital Light Processing Three‐Dimensional Printing

Advanced Intelligent Systems, EarlyView.
Metalearning‐based inverse optimization enables precise microscale three‐dimensional printing using a DLP system. Distorted structures from conventional printing are analyzed via neural network regression, which predicts optimal exposure time and mask design.
Jae Won Choi, Suhyeong Lim, Jeongsu Lee, Cheol Woo Ha   +3 more
wiley   +1 more source