• Publications
  • Influence
Learning to Represent Knowledge Graphs with Gaussian Embedding
TLDR
This paper switches to density-based embedding and propose KG2E for explicitly modeling the certainty of entities and relations, which learn the representations of KGs in the space of multi-dimensional Gaussian distributions. Expand
  • 190
  • 27
  • PDF
How to Generate a Good Word Embedding
TLDR
The authors analyze three critical components in training word embeddings: model, corpus, and training parameters. Expand
  • 221
  • 7
  • PDF
NNoculation: Broad Spectrum and Targeted Treatment of Backdoored DNNs
TLDR
This paper proposes a novel defense (NNoculation) against backdoored neural networks (BadNets) that, unlike existing defenses, makes minimal assumptions on the shape, size and location of backdoor triggers and BadNet's functioning. Expand
  • 9
  • 3
  • PDF
Adaptive Sliding Mode Based Disturbance Attenuation Tracking Control for Wheeled Mobile Robots
TLDR
This paper is devoted to investigating a composite controller for wheeled mobile robots in the presence of external disturbance and parametric uncertainty. Expand
  • 1
  • 1
Tensile strength and failure load of sutures for robotic surgery
BackgroundRobotic surgical platforms have seen increased use among minimally invasive gastrointestinal surgeons (von Fraunhofer et al. in J Biomed Mater Res 19(5):595–600, 1985.Expand
  • 12
Background Augmentation Generative Adversarial Networks (BAGANs): Effective Data Generation Based on GAN-Augmented 3D Synthesizing
TLDR
An automated vision data synthesis method, i.e., background augmentation generative adversarial networks (BAGANs), is proposed in this paper based on 3D modeling and the Generative Adversarial Network (GAN) algorithm. Expand
  • 7
De-noising methods for NMR logging echo signals based on wavelet transform
The signal-to-noise ratio (SNR) of the echo signals in nuclear magnetic resonance (NMR) is one of the most important factors that affect the effective application of NMR logging. Wavelet transformExpand
  • 13
Poisoning the (Data) Well in ML-Based CAD: A Case Study of Hiding Lithographic Hotspots
TLDR
We show that training data poisoning attacks are feasible and stealthy, demonstrating a backdoored neural network that performs normally on clean inputs but misbehaves on inputs when a backdoor trigger is present. Expand
  • 5
A Survey on Gaze Estimation
TLDR
A Survey on Gaze Estimation Techniques in Computer Vision and beyond. Expand
  • 9
Visualizing and exploring POI configurations of urban regions on POI-type semantic space
TLDR
This study proposes a novel framework for visualizing and exploring POIs on POI-type semantic space, with semantic relations of the types being considered. Expand
  • 5