Results 1 to 10 of about 27,364 (268)
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
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
Robust 2-bit Quantization of Weights in Neural Network Modeled by Laplacian Distribution
Advances in Electrical and Computer Engineering, 2021 Significant efforts are constantly involved in finding manners to decrease the number of bits required for quantization of neural network parameters. Although in addition to compression, in neural networks, the application of quantizer models that are ...
PERIC, Z. +3 more
doaj +1 more source
Distortion Minimization Hashing
IEEE Access, 2017 Application of the hashing method to large-scale image retrieval has drawn much attention because of the high efficiency and favorable accuracy of the method.
Tongtong Yuan, Weihong Deng, Jiani Hu
doaj +1 more source
Minisuperspace Quantization of f(T, B) Cosmology
Universe, 2021 We discuss the quantization in the minisuperspace for the generalized fourth-order teleparallel cosmological theory known as fT, B. Specifically we focus on the case where the theory is linear on the torsion scalar, in that consideration we are able to ...
Andronikos Paliathanasis
doaj +1 more source
Applied Sciences, 2020 This paper is an extension of the existing works on the frequency-domain-based bit flipping control strategy for stabilizing the single-bit high-order interpolative sigma delta modulator. In particular, this paper proposes the implementation and performs
Huishan Zhai, Bingo Wing-Kuen Ling
doaj +1 more source
IEEE Access, 2021 We consider a power constrained downlink communication scenario where energy efficiency, reliability, and latency take precedence over rate, as in some Internet of Things (IoT) applications.
Sherief Helwa, Naofal Al-Dhahir
doaj +1 more source
About its own time and the mass of the universe
St. Petersburg Polytechnical University Journal: Physics and Mathematics, 2021 A modification of the quantum theory of gravity in the case of a closed universe, in which the dynamics is reduced to the motion in the orbit of a group of general covariance, is proposed.
Gorobey Natalia +2 more
doaj +1 more source
Analysis of Application of Cluster Descriptions in Space of Characteristic Image Features
Data, 2018 In this paper, we propose an investigation of the properties of structural image recognition methods in the cluster space of characteristic features. Recognition, which is based on key point descriptors like SIFT (Scale-invariant Feature Transform), SURF
Oleksii Gorokhovatskyi +2 more
doaj +1 more source
Communication Efficient Federated Learning With Quantization-Aware Training Design
IEEE Transactions on Machine Learning in Communications and NetworkingModel quantization is an effective method that can improve communication efficiency in federated learning (FL). The existing FL quantization protocols almost stay at the level of post-training quantization (PTQ), which comes at the cost of large ...
Xiang Fang +4 more
doaj +1 more source