Identification of Causal Effects Using Instrumental Variables
Abstract We outline a framework for causal inference in settings where assignment to a binary treatment is ignorable, but compliance with the assignment is not perfect so that t...
Publications
Explore 134 academic publications
Showing 12 of
134 publications
Learning Deconvolution Network for Semantic Segmentation
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer ne...
GhostNet: More Features From Cheap Operations
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an importa...
Report 9: Impact of non-pharmaceutical interventions (NPIs) to reduce COVID19 mortality and healthcare demand
The global impact of COVID-19 has been profound, and the public health threat it represents is the most serious seen in a respiratory virus since the 1918 H1N1 influenza pandemi...
Evolutionary-scale prediction of atomic-level protein structure with a language model
Recent advances in machine learning have leveraged evolutionary information in multiple sequence alignments to predict protein structure. We demonstrate direct inference of full...
Random graphs with arbitrary degree distributions and their applications
Recent work on the structure of social networks and the internet has focused attention on graphs with distributions of vertex degree that are significantly different from the Po...
Present and Future of Surface-Enhanced Raman Scattering
The discovery of the enhancement of Raman scattering by molecules adsorbed on nanostructured metal surfaces is a landmark in the history of spectroscopic and analytical techniqu...
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
We present SpecAugment, a simple data augmentation method for speech\nrecognition. SpecAugment is applied directly to the feature inputs of a neural\nnetwork (i.e., filter bank ...
A cladistic analysis of phenotypic associations with haplotypes inferred from restriction endonuclease mapping and DNA sequence data. III. Cladogram estimation.
Abstract We previously developed a cladistic approach to identify subsets of haplotypes defined by restriction endonuclease mapping or DNA sequencing that are associated with si...
PCA-SIFT: a more distinctive representation for local image descriptors
Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) rec...