Convergence Results for Neural Networks via Electrodynamics
We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradi...
Publications
Explore 516 academic publications
Showing 12 of
516 publications
Fab
article Free AccessFab: content-based, collaborative recommendation Authors: Marko Balabanović Computer Science Department, Stanford University, Stanford, Calif. Computer Scienc...
The Functional Approach to the Study of Attitudes
Journal Article THE FUNCTIONAL APPROACH TO THE STUDY OF ATTITUDES Get access DANIEL KATZ DANIEL KATZ The author is Professor of Psychology at the University of Michigan, former ...
Randomised trial of intravenous streptokinase, oral aspirin, both, or neither among 17,187 cases of suspected acute myocardial infarction: ISIS-2. ISIS-2 (Second International Study of Infarct Survival) Collaborative Group.
17,187 patients entering 417 hospitals up to 24 hours (median 5 hours) after the onset of suspected acute myocardial infarction were randomised, with placebo control, between: (...
THE NUMBER OF ALLELES THAT CAN BE MAINTAINED IN A FINITE POPULATION
T has sometimes been suggested that the wild-type allele is not a single entity, I but rather a population of different isoalleles that are indistinguishable by any ordinary pro...
Striving for Simplicity: The All Convolutional Net
Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a sm...
Scattered Data Approximation
Many practical applications require the reconstruction of a multivariate function from discrete, unstructured data. This book gives a self-contained, complete introduction into ...
How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis
Journal Article How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis Get access C. Fraley, C. Fraley Department of Statistics, University of Wash...
Bayesian Inference of Species Trees from Multilocus Data
Until recently, it has been common practice for a phylogenetic analysis to use a single gene sequence from a single individual organism as a proxy for an entire species. With te...