Results 111 to 120 of about 22,800 (222)

Stochastic Computing for Hardware Implementation of Binarized Neural Networks

IEEE Access, 2019
Binarized neural networks, a recently discovered class of neural networks with minimal memory requirements and no reliance on multiplication, are a fantastic opportunity for the realization of compact and energy efficient inference hardware.
Tifenn Hirtzlin, Bogdan Penkovsky, Marc Bocquet, Jacques-Olivier Klein, Jean-Michel Portal, Damien Querlioz   +5 more
doaj   +1 more source

Efficient Exact Verification of Binarized Neural Networks

, 2020
To be published in NeurIPS ...
Jia, Kai, Rinard, Martin
openaire   +2 more sources

Distinct Roles of Cerebellar Afferent and Efferent Fiber Tracts in Craniocervical Dystonia

Movement Disorders, EarlyView.
Abstract Background The cerebellum has been widely implicated in the pathogenesis of craniocervical dystonia (CCD). Subthalamic nucleus deep brain stimulation (STN‐DBS) has emerged as an effective therapy for CCD. However, the roles of cerebellar afferent and efferent pathways in CCD pathogenesis and STN‐DBS treatment remain poorly understood ...
Bin Liu, Wenjie Li, Yanyang Zhang, Tao Yu, Zaixu Cui, Xiaoyu Xu, Junpeng Xu, Xin Chen, Jingyu Feng, Zhiqi Mao, Jun Yang   +10 more
wiley   +1 more source

Longitudinal Awake Mouse fMRI During Voluntary Locomotion Using Zero TE Imaging and a Novel Treadmill Training Protocol

Magnetic Resonance in Medicine, EarlyView.
ABSTRACT Purpose Functional MRI (fMRI) in awake rodents presents countless valuable opportunities for researchers to probe questions that may not be accessible through anesthetized models, such as voluntary locomotion. The commonly used echo planar imaging (EPI) sequence is highly sensitive to motion that occurs even outside of the imaging plane ...
Lauren Daley, Wen‐Ju Pan, Gopinath Kaundinya, Shella Keilholz   +3 more
wiley   +1 more source

Using deep learning to assess the toxicological effects of sublethal exposure of a novel green pesticide in a stored‐product beetle

Pest Management Science, EarlyView.
This study employs an AI‐driven multidisciplinary approach to increase our understanding of the toxicological effects of sublethal concentrations of carlina oxide on Prostephanus truncatus. Sublethal exposure to the carlina oxide induced changes in motor patterns and thigmotaxis, highlighting its potential role in integrated pest management strategies.
Anita Casadei, Maria C. Boukouvala, Gianluca Manduca, Nickolas G. Kavallieratos, Filippo Maggi, Marta Ferrati, Eleonora Spinozzi, Cesare Stefanini, Antonio DeSimone, Donato Romano   +9 more
wiley   +1 more source

TGBNN: Training Algorithm of Binarized Neural Network With Ternary Gradients for MRAM-Based Computing-in-Memory Architecture

IEEE Access
To build Neural Networks (NNs) on edge devices, Binarized Neural Network (BNN) has been proposed on the software side, while Computing-in-Memory (CiM) architecture has been proposed on the hardware side.
Yuya Fujiwara, Takayuki Kawahara
doaj   +1 more source

How AI and Digital Technologies Can Enhance Sustainable Livestock Manure Management: An Overview From Treatment to Distribution

Sustainable Development, EarlyView.
ABSTRACT Sustainable livestock manure management sits at the nexus of climate, nutrient circularity and water quality. This review explores how artificial intelligence (AI) and digital platforms are used across four management stages, that is, treatment, storage, valorisation and distribution, and figures out where integration fails to deliver ...
Zhan Shi, Feihong Liang, Francesco Marinello, Andrea Pezzuolo   +3 more
wiley   +1 more source

Brain Pericytes and Wnt/β‐Catenin Signaling Induce Functional Blood–Brain Barrier Phenotype in Human iPSC‐Derived Model

Small Methods, EarlyView.
This study shows that human iPSC‐derived endothelial cells acquire a functional blood–brain barrier phenotype when co‐cultured with brain pericytes and stimulated with CHIR‐99021, a Wnt/β‐catenin activator. This model recapitulates key barrier properties, inflammatory responses, and transcriptomic features of the native human BBB, offering new ...
Henrique Nogueira Pinto, Nine R. Kok, Philipp C. Hauger, Manon Karsten‐van Diepen, Michael de Kok, Nanne J. Paauw, Susanne M. A. van der Pol, Joline P. Nugteren‐Boogaard, Peter L. Hordijk, Stephanie D. Beekhuis‐Hoekstra, Susan Gibbs, Nienke M. de Wit, Helga E. de Vries   +12 more
wiley   +1 more source

PUMAA: Establishing a protocol for utilizing machine learning in forensic anthropological analyses

Journal of Forensic Sciences, EarlyView.
Abstract The use of machine learning (ML) models in forensic anthropology (FA) has increased in the last half decade; however, there is a lack of a standardized protocol on how to curate, use, and assess ML models. We introduce PUMAA (A Protocol for Utilizing Machine Learning in Forensic Anthropological Analyses), which includes a flowchart and a ...
Eman Faisal, Tracy L. Rogers
wiley   +1 more source

Synchronization dependent on spatial structures of a mesoscopic whole-brain network.

PLoS Computational Biology, 2019
Complex structural connectivity of the mammalian brain is believed to underlie the versatility of neural computations. Many previous studies have investigated properties of small subsystems or coarse connectivity among large brain regions that are often ...
Hannah Choi, Stefan Mihalas
doaj   +1 more source