M
Michael K. Ng
Researcher at University of Hong Kong
Publications - 658
Citations - 24376
Michael K. Ng is an academic researcher from University of Hong Kong. The author has contributed to research in topics: Cluster analysis & Computer science. The author has an hindex of 72, co-authored 608 publications receiving 20492 citations. Previous affiliations of Michael K. Ng include The Chinese University of Hong Kong & Vanderbilt University.
Papers
More filters
Book ChapterDOI
Modeling Gene Expression Network with PCA-NN on Continuous Inputs and Outputs Basis
TL;DR: In this work, the numerical modeling of the gene expression time series has been constructed with the principal component (PCA) and the neural network and the PCA-NN method outperforms the others.
Book ChapterDOI
A Variational Method for Expanding the Bit-Depth of Low Contrast Image
TL;DR: A variational approach containing an energy functional to determine a local mapping function for bit-depth expansion via a smoothing technique, such that each pixel can be adjusted locally to a high bit- depth value, in order to enhance low contrast images.
Posted Content
Co-Separable Nonnegative Matrix Factorization
Junjun Pan,Michael K. Ng +1 more
TL;DR: In this article, a Co-Separable Nonnegative Matrix Factorization (CoS-NMF) model was proposed, which requires that S is a sub-matrix of the input matrix.
Journal ArticleDOI
Stochastic Variance Reduced Gradient for affine rank minimization problem
TL;DR: In this paper , a stochastic variance reduced gradient descent (SVDGD) algorithm is proposed to solve the rank minimization problem, which consists of finding a matrix of minimum rank from linear measurements.
Journal ArticleDOI
Stability and Generalization of Graph Convolutional Networks in Eigen-domains
Michael K. Ng,Andy M. Yip +1 more
TL;DR: In this paper , a two-layer graph convolutional neural network with transductive semi-supervised learning is analyzed and the convergence of the generalization gap to zero is shown.