Results 151 to 160 of about 127,617 (265)

Ultrafast in‐memory computing and highly efficient deep neural networks driven by phase‐change memory materials with partially amorphous state transitions

open access: yesInfoScience, EarlyView.
This work addresses challenges including the nonlinear weight‐conductance update and the trade‐off between increasing melting uniformity and reducing solid‐to‐liquid transition time. It utilizes all four melting states to create an integrated framework for attaining in‐memory computing and deep neural network applications. The framework achieves a near‐
Kian‐Guan Lim   +7 more
wiley   +1 more source

Organic neuromorphic electronics powering intelligent sensory and edge computing systems

open access: yesInfoMat, EarlyView.
Organic electronic materials are promising candidates for neuromorphic sensing applications, including chemical, physical, visual, and multimodal sensing, owing to their mechanical softness, biocompatibility, and intrinsic ionic–electronic coupling.
Seungjun Woo   +5 more
wiley   +1 more source

Recent advances in data‐driven and artificial intelligence‐integrated perovskite solar cells: From design to self‐driving laboratories

open access: yesInfoMat, EarlyView.
To address the limitations of conventional trial‐and‐error approaches, perovskite solar cell research is shifting toward a new paradigm that utilizes datasets and AI. This review examines the fundamental elements of data‐driven and AI‐integrated research: data platforms, AI methodologies, and self‐driving laboratories, demonstrating how their ...
Jaehee Lee   +5 more
wiley   +1 more source

Intrinsic chiroptical responsivity in self‐powered organic photodiodes for polarization‐tunable optical convolution

open access: yesInfoMat, EarlyView.
Self‐powered chiral organic photodiodes function as polarization‐sensitive convolutional filters for circularly polarized light‐driven optical convolutional neural networks. This conceptually innovative architecture enables dynamic weight modulation, bias‐free operation, and exceptional noise resilience, boosting feature extraction fidelity from 0.15 ...
Lixuan Liu   +9 more
wiley   +1 more source

Deep learning‐based prediction of cervical lymph node metastasis and genetic alterations from whole‐slide images of thyroid cancer frozen sections

open access: yesInterdisciplinary Medicine, EarlyView.
Deep learning models accurately predict cervical lymph node metastasis and key genetic mutations (BRAF/TERT) directly from thyroid cancer frozen sections. This AI‐driven pipeline provides a rapid real‐time tool to guide intraoperative surgical decisions, helping to optimize surgical extent and prevent both over‐ and under‐treatment without the need for
Mingxing Qiu   +20 more
wiley   +1 more source

Home - About - Disclaimer - Privacy