• Publications
  • Influence
Scaling Up Kernel SVM on Limited Resources: A Low-Rank Linearization Approach
TLDR
Kernel support vector machines (SVMs) deliver state-of-the-art results in many real-world nonlinear classification problems, but the computational cost can be quite demanding. Expand
  • 61
  • 7
  • PDF
Neural computing for optimization and combinatorics
TLDR
In this book, a variety of optimization problems and combinatorics problems are presented by respective experts. Expand
  • 29
  • 4
A collaborative neurodynamic approach to global and combinatorial optimization
TLDR
In this paper, a collaborative neurodynamic optimization approach is proposed for global and combinatorial optimization that is globally convergent to global optimal solutions. Expand
  • 12
  • 4
Map-Based Localization Method for Autonomous Vehicles Using 3D-LIDAR *
Abstract Precise and robust localization is a significant task for autonomous vehicles in complex scenarios. The accurate position of autonomous vehicles is necessary for decision making and pathExpand
  • 32
  • 3
Pulmonary Nodule Detection in Volumetric Chest CT Scans Using CNNs-Based Nodule-Size-Adaptive Detection and Classification
TLDR
In computed tomography, automated detection of pulmonary nodules with a broad spectrum of appearance is still a challenge, especially, in the detection of small nodules. Expand
  • 9
  • 3
Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine
Extracting road networks from very-high-resolution (VHR) aerial and satellite imagery has been a long-standing problem. In this article, a neural-dynamic tracking framework is proposed to extractExpand
  • 83
  • 2
Analogue winner-take-all neural networks for determining maximum and minimum signals
  • J. Wang
  • Computer Science
  • 1 September 1994
TLDR
We propose two types of winner-take-all neural networks for determining maximum and minimum signals on-line and in parallel. Expand
  • 29
  • 2
Some q-rung orthopair fuzzy point weighted aggregation operators for multi-attribute decision making
TLDR
We propose a new class of point weighted aggregation operators to aggregate q-rung orthopair fuzzy information. Expand
  • 29
  • 2
ActiveHNE: Active Heterogeneous Network Embedding
TLDR
Heterogeneous network embedding (HNE) is a challenging task due to the diverse node types and/or diverse relationships between nodes. Expand
  • 13
  • 2
  • PDF