13 papers · ranked by Valyu relevance
Jelena Nikolić, Zoran Perić, Danijela Aleksić, Stefan Tomić + 2 more
Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the performance of three-bit post-training uniform quantization. The goal…
Gabriele Carcassi, Christine A. Aidala, Andrei Khrennikov, Carlos Mejía-Monasterio
'Carlos Mejía-Monasterio'] Measure theory is used in physics, not just to capture classical probability, but also to quantify the number of states. In previous works, we found that state quantification plays a foundational role in classical mechanics, and, therefore, we set ourselves to construct the quantum equivalent…
Hasindu Kariyawasam, Ramith Hettiarachchi, Quansan Yang, Alex Matlock + 6 more
Optical processors, built with “optical neurons”, can efficiently perform high-dimensional linear operations at the speed of light. Thus they are a promising avenue to accelerate large-scale linear computations. With the current advances in micro-fabrication, such optical processors can now be 3D fabricated, but with a…
Angel L. Cedeño, Ricardo Albornoz, Rodrigo Carvajal, Boris I. Godoy + 2 more
'Juan C. Agüero' 'Andrey V. Savkin'] Filtering and smoothing algorithms are key tools to develop decision-making strategies and parameter identification techniques in different areas of research, such as economics, financial data analysis, communications, and control systems. These algorithms are used to obtain an…
Chen Li, Lei Ma, Steve Furber
Compared with artificial neural networks (ANNs), spiking neural networks (SNNs) offer additional temporal dynamics with the compromise of lower information transmission rates through the use of spikes. When using an ANN-to-SNN conversion technique there is a direct link between the activation bit precision of the…
Xuefu Sui, Qunbo Lv, Changjun Ke, Mingshan Li + 4 more
'Haiyang Yu' 'Zheng Tan' 'Hai Dong'] In the field of edge computing, quantizing convolutional neural networks (CNNs) using extremely low bit widths can significantly alleviate the associated storage and computational burdens in embedded hardware, thereby improving computational efficiency. However, such quantization…
Xia Yu, Huaiyu Zhuang, Yani Cui, Jiaxian Deng + 2 more
'Haixia Long'] 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 quantization algorithms for the Hue Saturation Intensity…
Joonhyuk Yoo, Guenwoo Ban, Weichuan Zhang, Yanbing Li + 2 more
'Jin Lu'] With the rapid growth of sensor technology and computer vision, efficient deep learning models are essential for real-time image feature extraction in resource-constrained environments. However, most existing quantized deep neural networks (DNNs) are highly sensitive to outliers, leading to severe performance…
Mozhgan A. Farahani, Alireza Vahid, Allison E. Goodwell, Luciano Telesca
'Luciano Telesca'] Ecohydrological models vary in their sensitivity to forcing data and use available information to different extents. We focus on the impact of forcing precision on ecohydrological model behavior particularly by quantizing, or binning, time-series forcing variables. We use rate-distortion theory to…
Shingo Yamauchi, Masaki Kawamura, Alessandro Piva
We propose a neural-network-based watermarking method that introduces the quantized activation function that approximates the quantization of JPEG compression. Many neural-network-based watermarking methods have been proposed. Conventional methods have acquired robustness against various attacks by introducing an…
Jiulu Gong, Qunlin Chen, Wei Zhu, Zepeng Wang + 1 more
Block compressed sensing (BCS) is a promising method for resource-constrained image/video coding applications. However, the quantization of BCS measurements has posed a challenge, leading to significant quantization errors and encoding redundancy. In this paper, we propose a quantization method for BCS measurements…
David Ellerman, Dennis Dieks, Michael Cuffaro, Stephan Hartmann
The new logic of partitions is dual to the usual Boolean logic of subsets (usually presented only in the special case of the logic of propositions) in the sense that partitions and subsets are category-theoretic duals. The new information measure of logical entropy is the normalized quantitative version of partitions.…
Roberto Leporini, Davide Pastorello
Optimal measurements for the discrimination of quantum states are useful tools for classification problems. In order to exploit the potential of quantum computers, feature vectors have to be encoded into quantum states represented by density operators. However, quantum-inspired classifiers based on nearest mean and on…