Publications

Representation Learning: A Review and New Perspectives

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more...

Induction of decision trees

Neural Networks for Pattern Recognition

Abstract This book provides the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basi...

Squeeze-and-Excitation Networks

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial a...

Scale-space and edge detection using anisotropic diffusion

The scale-space technique introduced by Witkin involves generating coarser resolution images by convolving the original image with a Gaussian kernel. This approach has a major d...

Generative adversarial networks

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a c...

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we conside...

An Iterative Image Registration Technique with an Application to Stereo Vision

Image registration finds a variety of applications in computer vision. Unfortunately, traditional image registration techniques tend to be costly. We present a new image registr...

A training algorithm for optimal margin classifiers

A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classif...

Aggregated Residual Transformations for Deep Neural Networks

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transfor...

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation

Accelerating the discovery of advanced materials is essential for human welfare and sustainable, clean energy. In this paper, we introduce the Materials Project (www.materialspr...

Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences

Abstract Motivation: In 2001 and 2002, we published two papers (Bioinformatics, 17, 282–283, Bioinformatics, 18, 77–82) describing an ultrafast protein sequence clustering progr...