Results 1 to 10 of about 369,200 (324)
Quantized Graph Neural Networks for Image Classification
Mathematics, 2023 Researchers have resorted to model quantization to compress and accelerate graph neural networks (GNNs). Nevertheless, several challenges remain: (1) quantization functions overlook outliers in the distribution, leading to increased quantization errors; (
Xinbiao Xu +3 more
doaj +1 more source
BMC Plant Biology, 2023 Background Rhamnus utilis Decne (Rhamnaceae) is an ecologically and economically important tree species. The growing market demands and recent anthropogenic impacts to R. utilis forests has negatively impacted its populations severely. However, little is
Song Guiquan +7 more
doaj +1 more source
How to Secure Valid Quantizations
Entropy, 2022 Canonical quantization has created many valid quantizations that require infinite-line coordinate variables. However, the half-harmonic oscillator, which is limited to the positive coordinate half, cannot receive a valid canonical quantization because of
John R. Klauder
doaj +1 more source
A dichotomy color quantization algorithm for the HSI color space
Scientific Reports, 2023 Color quantization is used to obtain an image with the same number of pixels as the original but represented using fewer colors. Most existing color quantization algorithms are based on the Red Green Blue (RGB) color space, and there are few color ...
Xia Yu +5 more
doaj +1 more source
Design Exploration of ReRAM-Based Crossbar for AI Inference
IEEE Access, 2021 ReRAM-based crossbar designs utilizing mixed-signal implementation has gained importance due to their low power, small size, low cost, and high throughput especially for multiply-and-add operations in AI-related applications.
Yasmin Halawani +2 more
doaj +1 more source
Quantization and Deployment of Deep Neural Networks on Microcontrollers
Sensors, 2021 Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design.
Pierre-Emmanuel Novac +4 more
doaj +1 more source
Training and Inference of Optical Neural Networks with Noise and Low-Bits Control
Applied Sciences, 2021 Optical neural networks (ONNs) are getting more and more attention due to their advantages such as high-speed and low power consumption. However, in a non-ideal environment, the noise and low-bits control may heavily lead to a decrease in the accuracy of
Danni Zhang +9 more
doaj +1 more source
Learning Sparse Low-Precision Neural Networks With Learnable Regularization
IEEE Access, 2020 We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations.
Yoojin Choi +2 more
doaj +1 more source
Support and Optimization of Multi-Granularity Quantization Framework for Deep Learning Compiler [PDF]
Jisuanji gongchengWith the increasing demand for the deployment of large models by major manufacturers, the accuracy of the single quantization method of deep learning compiler Tensor Virtual Machine (TVM) has decreased, and this method is no longer sufficient to satisfy ...
WEI Mingkang, LI Jianan, HAN Lin, GAO Wei, ZHAO Rongcai, WANG Hongsheng
doaj +1 more source
Quantized passive filtering for switched delayed neural networks
Nonlinear Analysis, 2021 The issue of quantized passive filtering for switched delayed neural networks with noise interference is studied in this paper. Both arbitrary and semi-Markov switching rules are taken into account.
Youmei Zhou +3 more
doaj +1 more source