Training Very Deep Networks
Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and tra...
Publications
Explore 498 academic publications
Showing 12 of
498 publications
Mitochondrial portraits of human populations using median networks.
Abstract Analysis of variation in the hypervariable region of mitochondrial DNA (mtDNA) has emerged as an important tool for studying human evolution and migration. However, att...
Phylogeny Estimation and Hypothesis Testing Using Maximum Likelihood
One of the strengths of the maximum likelihood method of phylogenetic estimation is the ease with which hypotheses can be formulated and tested. Maximum likelihood analysis of D...
Molecular Mechanisms of Antibody Somatic Hypermutation
Functional antibody genes are assembled by V-D-J joining and then diversified by somatic hypermutation. This hypermutation results from stepwise incorporation of single nucleoti...
Distributed representations
Computer Science Department
Network In Network
Abstract: We propose a novel deep network structure called In Network (NIN) to enhance model discriminability for local patches within the receptive field. The conventional con...
Linear Smoothers and Additive Models
We study linear smoothers and their use in building nonparametric regression models. In the first part of this paper we examine certain aspects of linear smoothers for scatterpl...
The impact of antenna diversity on the capacity of wireless communication systems
For a broad class of interference-dominated wireless systems including mobile, personal communications, and wireless PBX/LAN networks, the authors show that a significant increa...
Sorting single molecules: application to diagnostics and evolutionary biotechnology.
A method is described that provides for detection and identification of single molecules in solution. The method is based on fluorescence correlation spectroscopy, which records...
Comparison of Bayesian and maximum-likelihood inference of population genetic parameters
Abstract Comparison of the performance and accuracy of different inference methods, such as maximum likelihood (ML) and Bayesian inference, is difficult because the inference me...