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...
Explore 193 academic publications
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...
article Free AccessFab: content-based, collaborative recommendation Authors: Marko Balabanović Computer Science Department, Stanford University, Stanford, Calif. Computer Scienc...
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 ...
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...
Many practical applications require the reconstruction of a multivariate function from discrete, unstructured data. This book gives a self-contained, complete introduction into ...
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...
If Thomas Kuhn (1962) is correct, a field of inquiry develops in stages. Some members of a field of inquiry recognize anomalies in the foundational beliefs and seek better expla...
Journal Article A predictive approach to the random effect model Get access SEYMOUR GEISSER SEYMOUR GEISSER School of Statistics, University of MinnesotaMinneapolis Search for o...
This book, first published in 2006, presents an introduction to the methodology of structural equation modeling, illustrates its use, and goes on to argue that it has revolution...
Journal Article An improved Bonferroni procedure for multiple tests of significance Get access R. J. SIMES R. J. SIMES Ludwig Institute for Cancer Research, University of Sydney...