-
Article
Inter-feature Relationship Certifies Robust Generalization of Adversarial Training
Whilst adversarial training has been shown as a promising wisdom to promote model robustness in computer vision and machine learning, adversarially trained models often suffer from poor robust generalization o...
-
Article
Comparative Analysis of the Complete Mitochondrial Genomes of Three Sisoridae (Osteichthyes, Siluriformes) and the Phylogenetic Relationships of Sisoridae
The family Sisoridae is one of the largest and most diverse Asiatic catfish families, with most species occurring in the water systems of the Qinhai-Tibetan Plateau and East Himalayas. At present, the phylogen...
-
Article
Geometry-enhanced pretraining on interatomic potentials
Machine learning interatomic potentials (MLIPs) describe the interactions between atoms in materials and molecules by learning them from a reference database generated by ab initio calculations. MLIPs can accu...
-
Article
Open AccessGlobal burden and risk factors of gastritis and duodenitis: an observational trend study from 1990 to 2019
In recent years, there has been a global trend of aging, which has resulted in significant changes to the burden of gastritis and duodenitis (GD). Using the global burden of disease (GBD) database spanning 199...
-
Article
Open AccessThe causal effect of reproductive factors on pelvic floor dysfunction: a Mendelian randomization study
Pelvic floor dysfunction (PFD) is an extremely widespread urogynecologic disorder, the prevalence of which increases with aging. PFD has severely affected women’s quality of life and has been called a social c...
-
Article
Daphnia sp. (Branchiopoda: Cladocera) Mitochondrial Genome Gene Rearrangement and Phylogenetic Position Within Branchiopoda
In high-altitude (4500 m) freshwater lakes, Daphnia is the apex species and the dominant zooplankton. It frequently dwells in the same lake as the Gammarid. Branchiopoda, a class of Arthropoda, Crustacea, is a re...
-
Article
Robust generative adversarial network
Generative Adversarial Networks (GANs) are one of the most popular and powerful models to learn the complex high dimensional distributions. However, they usually suffer from instability and generalization issu...
-
Article
Open AccessThe causal effect of educational attainment on stress urinary incontinence: a two-sample mendelian randomization study
Stress urinary incontinence (SUI) is characterized by involuntary urine leakage in response to increased abdominal pressure, such as coughing, laughing, or sneezing. It significantly affects women’s quality of...
-
Article
The complete mitochondrial genome of Hemigrapsus sinensis (Brachyura, Grapsoidea, Varunidae) and its phylogenetic position within Grapsoidea
In this study, the complete mitogenome of Hemigrapsus sinensis was the first identified and analyzed.
-
Article
The complete mitochondrial genome of Parachiloglanis hodgarti and its phylogenetic position within Sisoridae
The complete mitogenome of Parachiloglanis hodgarti was sequenced and characterized, which is the first mitogenome of the genus Parachiloglanis within Sisoridae. The mitogenome is 16 511-bp long and included 13 p...
-
Article
Re-thinking model robustness from stability: a new insight to defend adversarial examples
We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a ...
-
Article
Improving generative adversarial networks with simple latent distributions
Generative Adversarial Networks (GANs) have drawn great attention recently since they are the powerful models to generate high-quality images. Although GANs have achieved great success, they usually suffer fro...
-
Article
Altered properties of brain white matter structural networks in patients with nasopharyngeal carcinoma after radiotherapy
Previous neuroimaging studies revealed radiation-induced brain injury in patients with nasopharyngeal carcinoma (NPC) in the years after radiotherapy (RT). These injuries may be associated with structural and ...
-
Article
Common and specific altered amplitude of low-frequency fluctuations in Parkinson’s disease patients with and without freezing of gait in different frequency bands
Freezing of gait (FOG), a disabling symptom of Parkinson’s disease (PD), severely affects PD patients’ life quality. Previous studies found neuropathologies in functional connectivity related to FOG, but few s...
-
Article
Nanocomposites consisting of nanoporous platinum-silicon and graphene for electrochemical determination of bisphenol A
Three-dimensional nanoporous PtSi (NP-PtSi) alloy was prepared by dealloying ternary PtSiAl alloy ribbons. By combining the nanoporous morphology of PtSi and graphene (GR), a new composite material was develop...
-
Article
Abnormal Effective Connectivity of the Anterior Forebrain Regions in Disorders of Consciousness
A number of studies have indicated that disorders of consciousness result from multifocal injuries as well as from the impaired functional and anatomical connectivity between various anterior forebrain regions...
-
Article
Plasticity in deep and superficial white matter: a DTI study in world class gymnasts
Brain white matter (WM) could be generally categorized into two types, deep and superficial WM. Studies combining these two types WM are important for a better understanding of brain plasticity induced by moto...
-
Article
Learning from Few Samples with Memory Network
Neural networks (NN) have achieved great successes in pattern recognition and machine learning. However, the success of a NN usually relies on the provision of a sufficiently large number of data samples as tr...
-
Chapter and Conference Paper
Improve Deep Learning with Unsupervised Objective
We propose a novel approach capable of embedding the unsupervised objective into hidden layers of the deep neural network (DNN) for preserving important unsupervised information. To this end, we exploit a very...
-
Chapter and Conference Paper
Learning from Few Samples with Memory Network
Neural Networks (NN) have achieved great success in pattern recognition and machine learning. However, the success of NNs usually relies on a sufficiently large number of samples. When fed with limited data, N...
