Results 161 to 170 of about 1,893,473 (266)
A training‐free two‐stage BO–RL framework extracts compact model parameters for a‐IGZO TFTs, reaching BO‐level fitting quality at a constant per‐simulation optimization cost. Bayesian optimization performs exploration and provides an optimized starting point.
Seunghyun Son +4 more
wiley +1 more source
Motion artifacts in electrocardiographic signals, conventionally dismissed as noise, are shown to encode discriminative activity information. A smart t‐shirt fusing textile strain sensors with textile ECG electrodes, processed through a complex‐valued residual network, recognizes 12 sport activities.
Nada Al‐azzawi +4 more
wiley +1 more source
PRISM, a Bidirectional NMR Foundation Model: From Peak List to Structure and Back
Structure elucidation from NMR can consume an expert for hours or even days. PRISM addresses this with a bidirectional transformer trained on 1.19 M real experimental spectra: it translates 1H and 13C peak lists into structures with 60.1% stereo‐aware top‐1 accuracy (72.5% stereo‐unaware), and, working in reverse, predicts spectra back from structures,
Ajnabiul Hoque, Frank Glorius
wiley +2 more sources
Spatially programmable origami networks enable high-density mechanical computing for autonomous robotics. [PDF]
Hu X, Tan T, Chen Y, Yan Z.
europepmc +1 more source
Secure Fusion‐X harmonizes unstructured NVD descriptions with structured CVSS/CWE/CPE metadata via decision‐level fusion, overcoming the fragility of traditional unimodal models. Automated assessment of software vulnerability exploitability is essential for intelligent cyber defense, yet its effectiveness is often hindered by unstable, delayed, or ...
Mona Dolati +3 more
wiley +1 more source
Optimized NCFET-based approximate multiplier for energy-aware image applications. [PDF]
Srinivas MBR, Elango K.
europepmc +1 more source
Vertical NAND Flash Memory‐Based Bayesian Neural Networks With Intrinsic Gaussian Weight Sampling
Commercial vertical NAND flash memory supports Bayesian neural networks by using paired cells to produce bell‐shaped weight distributions. Read voltage controls their spread without additional memory cells or changes to the array structure. Simulations based on device measurements demonstrate improved uncertainty estimation and accuracy gains of up to ...
Sung‐Ho Park +8 more
wiley +1 more source
DSLHash: Lightweight Hash Function Based on SVSC 4D Chaotic System and Dynamic Substitution Layers. [PDF]
Zhang J +6 more
europepmc +1 more source
Programable Acoustic Single‐Cell Manipulation With Model‐Free Machine Learning
Closed‐loop control with ultrasound enables precise, noninvasive manipulation of individual cells inside a microfluidic device using a model‐free reinforcement learning‐inspired algorithm, achieving 2D control using a single piezoelectric transducer.
Alexander Edthofer +3 more
wiley +1 more source
Metazoan lagging-strand DNA synthesis is distributive. [PDF]
Lynch LD, Park J, Chistol G.
europepmc +1 more source

