Results 111 to 120 of about 22,912 (307)

Spike-RISC: Algorithm/ISA Co-Optimization for Efficient SNNs on RISC-V

IEEE Access
Artificial intelligence has proven its benefits in many domains. Yet, traditional deep learning models are still too energy and compute-intensive for resource-constrained edge environments.
Ipek Akdeniz, Sandy A. Wasif, Paul R. Genssler, Hussam Amrouch   +3 more
doaj   +1 more source

Thermally activated delayed fluorescence exciplex sensitizers with fast reverse intersystem crossing for improving efficiency stability of organic light‐emitting diodes based on multi‐resonance emitters

FlexMat, EarlyView.
Two exciplex emitters are constructed based on a host‐guest doping strategy, and their exciton dynamics processes are investigated in depth. High‐performance OLEDs are fabricated by employing these exciplexes as emitters or sensitizers, providing excellent electroluminescence efficiencies and low efficiency roll‐offs.
Jingwen Xu, Min Wang, Jinshi Li, Ben Zhong Tang, Zujin Zhao   +4 more
wiley   +1 more source

MARVEL: An End-to-End Framework for Generating Model-Class Aware Custom RISC-V Extensions for Lightweight AI

IEEE Open Journal of Circuits and Systems
Deploying deep neural networks (DNNs) on resource-constrained IoT devices remains a challenging problem, often requiring hardware modifications tailored to individual AI models.
M. Ajay Kumar, Cian O'Mahoney, Pedro Kreutz Werle, Shreejith Shanker, Dimitrios S. Nikolopoulos, Bo Ji, Hans Vandierendonck, Deepu John   +7 more
doaj   +1 more source

A Heterogeneous RISC-V Processor for Efficient DNN Application in Smart Sensing System. [PDF]

Sensors (Basel), 2021
Zhang H, Wu X, Du Y, Guo H, Li C, Yuan Y, Zhang M, Zhang S.   +7 more
europepmc   +1 more source

Epigenetic Regulation in the Pathogenesis of Renal Inflammation: Insights and Therapeutic Potentials

iNew Medicine, EarlyView.
ABSTRACT Renal inflammation is a common pathological process in various kidney diseases, often initiated by factors such as toxins, ischemia, or autoimmune reactions. This inflammatory response can result in structural damage and a rapid decline in renal function.
Yu‐Hang Dong, Xiao‐Yu Shen, Han‐Cheng Jin, Xiang‐Yu Li, Hao He, Xiao‐Ming Meng   +5 more
wiley   +1 more source

Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC With 2–8 b DNN Acceleration and 30%-Boost Adaptive Body Biasing

, 2023
Francesco Conti, Gianna Paulin, Angelo Garofalo, Davide Rossi, Alfio Di Mauro, Georg Rutishauser, Gianmarco Ottavi, Manuel Eggiman, Hayate Okuhara, Luca Benini   +9 more
openalex   +2 more sources

HardScope: Thwarting DOP with Hardware-assisted Run-time Scope Enforcement

, 2017
Widespread use of memory unsafe programming languages (e.g., C and C++) leaves many systems vulnerable to memory corruption attacks. A variety of defenses have been proposed to mitigate attacks that exploit memory errors to hijack the control flow of the
Asokan, N., Dessouky, Ghada, Lehikoinen, Aaro, Nyman, Thomas, Paverd, Andrew, Sadeghi, Ahmad-Reza, Zeitouni, Shaza   +6 more
core  

Diagnostic Performance of Ultrasound to Evaluate Mild Hip Osteoarthritis: Comparison With Radiography and MRI

Journal of Clinical Ultrasound, EarlyView.
A moderate‐sized femoral neck osteophyte (white arrow) in US (A), anteroposterior CR (B), and MRI (C). Additional osteoarthritis‐related changes (arrowheads) are visible in CR and MR, but not in US. US and CR demonstrated similar moderate diagnostic capability to detect mild hip osteoarthritis and were associated with increased hip pain.
Antti Kemppainen, Saana Kaartinen, Mika T. Nevalainen   +2 more
wiley   +1 more source

An Educational RISC-V-Based 16-Bit Processor

Chips
This work introduces a novel custom-designed 16-bit RISC-V processor, intended for educational purposes and for use in low-resource equipment. The implementation, despite providing registers of 16 bits, is based on RV32E RISC-V ISA, but with some key ...
Jecel Mattos de Assumpção, Oswaldo Hideo Ando, Hugo Puertas de Araújo, Mario Gazziro   +3 more
doaj   +1 more source

Challenges and Opportunities in Machine Learning for Light‐Emitting Polymers

Macromolecular Rapid Communications, EarlyView.
The performance of light‐emitting polymers emerges from coupled effects of chemical diversity, morphology, and exciton dynamics across multiple length scales. This Perspective reviews recent design strategies and experimental challenges, and discusses how machine learning can unify descriptors, data, and modeling approaches to efficiently navigate ...
Tian Tian, Yinyin Bao
wiley   +1 more source