Results 81 to 90 of about 1,314,055 (250)
IEEE Access, 2023 As the applications for artificial intelligence are growing rapidly, numerous network compression algorithms have been developed to restrict computing resources such as smartphones, edge, and IoT devices. Knowledge distillation (KD) leverages soft labels
Ju Yeon Kang, Chang Ho Ryu, Tae Hee Han
doaj +1 more source
Learning Surrogate Models of Document Image Quality Metrics for Automated Document Image Processing
, 2017 Computation of document image quality metrics often depends upon the availability of a ground truth image corresponding to the document. This limits the applicability of quality metrics in applications such as hyperparameter optimization of image ...
Hast, Anders +2 more
core +1 more source
Advanced Robotics Research, EarlyView.Permanent magnet putty (PMP) integrates high‐coercivity NdFeB particles with a dynamic polyborosiloxane–Ecoflex matrix, achieving rapid self‐healing (90% mechanical recovery in 10 s) and magnetic recovery within 20 min. With twice the sensitivity of commercial putties, PMP enables precise 5–30 N force detection and discrimination between pressing and ...
Ruotong Zhao +5 more
wiley +1 more source
Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge
IEEE Access, 2019 Deep neural networks (DNNs) have recently achieved remarkable performance in a myriad of applications, ranging from image recognition to language processing.
Corey Lammie +3 more
doaj +1 more source
Remote Sensing, 2021 Change detection is an important task in identifying land cover change in different periods. In synthetic aperture radar (SAR) images, the inherent speckle noise leads to false changed points, and this affects the performance of change detection.
Liangliang Li, Hongbing Ma, Zhenhong Jia
doaj +1 more source
Advanced Science, EarlyView.This study uncovers a new allosteric site in the Josephin domain of ataxin‐3 targeted by the molecular tweezer CLR01, which modulates protein aggregation, improves synaptic function in neuronal cells, and delays motor dysfunction in animal models.
Alexandra Silva +28 more
wiley +1 more source
Discretization Based Solutions for Secure Machine Learning Against Adversarial Attacks
IEEE Access, 2019 Adversarial examples are perturbed inputs that are designed (from a deep learning network's (DLN) parameter gradients) to mislead the DLN during test time.
Priyadarshini Panda +2 more
doaj +1 more source
Pattern Classification Using Quantized Neural Networks for FPGA-Based Low-Power IoT Devices
Sensors, 2022 With the recent growth of the Internet of Things (IoT) and the demand for faster computation, quantized neural networks (QNNs) or QNN-enabled IoT can offer better performance than conventional convolution neural networks (CNNs).
Manas Ranjan Biswal +5 more
doaj +1 more source
Searching Similarity Measure for Binarized Neural Networks
, 2022 Being a promising model to be deployed in resource-limited devices, Binarized Neural Networks (BNNs) have drawn extensive attention from both academic and industry. However, comparing to the full-precision deep neural networks (DNNs), BNNs suffer from non-trivial accuracy degradation, limiting its applicability in various domains.
Li, Yanfei, Li, Ang, Yu, Huimin
openaire +2 more sources
A new approach to binarizing neural networks [PDF]
2016 International SoC Design Conference (ISOCC), 2016 As deep neural networks grow larger, they suffer from a huge number of weights, and thus reducing the overhead of handling those weights becomes one of key challenges nowadays. This paper presents a new approach to binarizing neural networks, where the weights are pruned and forced to take degenerate binary values.
Jungwoo Seo +3 more
openaire +1 more source