Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond
Deep neural networks have been well-known for their superb handling of various machine
learning and artificial intelligence tasks. However, due to their over-parameterized black-box …
learning and artificial intelligence tasks. However, due to their over-parameterized black-box …
Intelligent power control for spectrum sharing in cognitive radios: A deep reinforcement learning approach
We consider the problem of spectrum sharing in a cognitive radio system consisting of a
primary user and a secondary user. The primary user and the secondary user work in a non-…
primary user and a secondary user. The primary user and the secondary user work in a non-…
Ot-flow: Fast and accurate continuous normalizing flows via optimal transport
A normalizing flow is an invertible mapping between an arbitrary probability distribution and
a standard normal distribution; it can be used for density estimation and statistical inference. …
a standard normal distribution; it can be used for density estimation and statistical inference. …
Millimeter wave channel estimation via exploiting joint sparse and low-rank structures
We consider the problem of channel estimation for millimeter wave (mmWave) systems,
where, to minimize the hardware complexity and power consumption, an analog transmit …
where, to minimize the hardware complexity and power consumption, an analog transmit …
Delta: Deep learning transfer using feature map with attention for convolutional networks
Transfer learning through fine-tuning a pre-trained neural network with an extremely large
dataset, such as ImageNet, can significantly accelerate training while the accuracy is …
dataset, such as ImageNet, can significantly accelerate training while the accuracy is …
Adaptive consistency regularization for semi-supervised transfer learning
While recent studies on semi-supervised learning have shown remarkable progress in leveraging
both labeled and unlabeled data, most of them presume a basic setting of the model is …
both labeled and unlabeled data, most of them presume a basic setting of the model is …
The effect of revenue diversification on bank profitability and risk during the COVID-19 pandemic
Banks can potentially reduce the variability of their revenue by diversifying beyond traditional
lending activities into noninterest revenue sources. We investigate the effect of the COVID-…
lending activities into noninterest revenue sources. We investigate the effect of the COVID-…
Pay attention to features, transfer learn faster CNNs
Deep convolutional neural networks are now widely deployed in vision applications, but a
limited size of training data can restrict their task performance. Transfer learning offers the …
limited size of training data can restrict their task performance. Transfer learning offers the …
Antidote or Trojan horse for submerged macrophytes: Role of microplastics in copper toxicity in aquatic environments
Due to their unique surface structures and physicochemical properties, microplastics (MPs)
can adsorb other contaminants, thus impacting their toxicity and fate in aquatic ecosystems. …
can adsorb other contaminants, thus impacting their toxicity and fate in aquatic ecosystems. …
Prevalence of and risk factors for fatty liver in a general population of Shanghai, China
JG Fan, J Zhu, XJ Li, L Chen, L Li, F Dai, F Li… - Journal of …, 2005 - Elsevier
BACKGROUND/AIMS: To determine the prevalence and risk factors of fatty liver (FL) among
Shanghai adults. METHODS: A cross-sectional ultrasonographic survey with randomized …
Shanghai adults. METHODS: A cross-sectional ultrasonographic survey with randomized …