Showing 91 to 100 of 145 articles
Clear Filters
Neural networks : the official journal of the International Neural Network Society
Jan 20, 2021
Deep learning-based methods have shown to achieve excellent results in a variety of domains, however, some important assets are absent. Quality scalability is one of them. In this work, we introduce a novel and generic neural network layer, named Mas...
Computational and mathematical methods in medicine
Jan 20, 2021
Deep learning has shown potential in significantly improving performance for undersampled magnetic resonance (MR) image reconstruction. However, one challenge for the application of deep learning to clinical scenarios is the requirement of large, hig...
Neural networks : the official journal of the International Neural Network Society
Dec 25, 2020
The goal of monaural speech enhancement is to separate clean speech from noisy speech. Recently, many studies have employed generative adversarial networks (GAN) to deal with monaural speech enhancement tasks. When using generative adversarial networ...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Dec 4, 2020
This paper presents an iterative training of neural networks for intra prediction in a block-based image and video codec. First, the neural networks are trained on blocks arising from the codec partitioning of images, each paired with its context. Th...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Nov 23, 2020
The use of l (p = 1,2) norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent w...
Magnetic resonance in medicine
Oct 26, 2020
PURPOSE: We aim to leverage the power of deep-learning with high-fidelity training data to improve the reliability and processing speed of hemodynamic mapping with MR fingerprinting (MRF) arterial spin labeling (ASL).
Sensors (Basel, Switzerland)
Oct 23, 2020
In recent years, deep learning models have achieved remarkable successes in various applications, such as pattern recognition, computer vision, and signal processing. However, high-performance deep architectures are often accompanied by a large stora...
PLoS computational biology
Oct 15, 2020
It has extensively been documented that human memory exhibits a wide range of systematic distortions, which have been associated with resource constraints. Resource constraints on memory can be formalised in the normative framework of lossy compressi...
Neural networks : the official journal of the International Neural Network Society
Sep 19, 2020
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for computational...
Neural networks : the official journal of the International Neural Network Society
Sep 17, 2020
Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by ...