Long Short-Term Memory
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We brief...
Publications
Explore 135 academic publications
Showing 12 of
135 publications
Regression Shrinkage and Selection Via the Lasso
SUMMARY We propose a new method for estimation in linear models. The ‘lasso’ minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients b...
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Sca...
Molecular dynamics with coupling to an external bath
In molecular dynamics (MD) simulations the need often arises to maintain such parameters as temperature or pressure rather than energy and volume, or to impose gradients for stu...
Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation
Traditional econometric models assume a constant one-period forecast variance. To generalize this implausible assumption, a new class of stochastic processes called autoregressi...
The magical number seven, plus or minus two: Some limits on our capacity for processing information.
First, the span of absolute judgment and the span of immediate memory impose severe limitations on the amount of information that we are able to receive, process, and remember. ...
The magical number seven, plus or minus two: Some limits on our capacity for processing information.
First, the span of absolute judgment and the span of immediate memory impose severe limitations on the amount of information that we are able to receive, process, and remember. ...
An Analysis of Transformations
Summary In the analysis of data it is often assumed that observations y 1, y 2, …, yn are independently normally distributed with constant variance and with expectations specifi...
<i>Planck</i> 2018 results
We present cosmological parameter results from the final full-mission Planck measurements of the cosmic microwave background (CMB) anisotropies, combining information from the t...
Applied Longitudinal Data Analysis
Abstract Change is constant in everyday life. Infants crawl and then walk, children learn to read and write, teenagers mature in myriad ways, and the elderly become frail and fo...
First‐Year <i>Wilkinson Microwave Anisotropy Probe</i> ( <i>WMAP</i> ) Observations: Determination of Cosmological Parameters
WMAP precision data enables accurate testing of cosmological models. We find that the emerging standard model of cosmology, a flat Λ−dominated universe seeded by a nearly scalei...