IEEE transactions on neural networks and learning systems
Oct 5, 2022
There are two main categories of face sketch synthesis: data- and model-driven. The data-driven method synthesizes sketches from training photograph-sketch patches at the cost of detail loss. The model-driven method can preserve more details, but the...
IEEE transactions on neural networks and learning systems
Oct 5, 2022
In the brief, delayed impulsive control is investigated for the synchronization of chaotic neural networks. In order to overcome the difficulty that the delays in impulsive control input can be flexible, we utilize the concept of average impulsive de...
IEEE transactions on neural networks and learning systems
Oct 5, 2022
This article is devoted to investigating finite-time synchronization (FTS) for coupled neural networks (CNNs) with time-varying delays and Markovian jumping topologies by using an intermittent quantized controller. Due to the intermittent property, i...
IEEE transactions on neural networks and learning systems
Oct 5, 2022
Model quantization is essential to deploy deep convolutional neural networks (DCNNs) on resource-constrained devices. In this article, we propose a general bitwidth assignment algorithm based on theoretical analysis for efficient layerwise weight and...
PloS one
Oct 5, 2022
BACKGROUND: Measurement of care quality and safety mainly relies on abstracted administrative data. However, it is well studied that administrative data-based adverse event (AE) detection methods are suboptimal due to lack of clinical information. El...
Computers in biology and medicine
Oct 4, 2022
AIM OF STUDY: Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
Binarized neural networks (BNNs) have drawn significant attention in recent years, owing to great potential in reducing computation and storage consumption. While it is attractive, traditional BNNs usually suffer from slow convergence speed and drama...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can adapt their structures or parameters to different input...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
When viewing omnidirectional images (ODIs), viewers can access different viewports via head movement (HM), which sequentially forms head trajectories in spatial-temporal domain. Thus, head trajectories play a key role in modeling human attention on O...
IEEE transactions on pattern analysis and machine intelligence
Oct 4, 2022
Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversit...