P
Patrick W. Gallagher
Publications - 5
Citations - 3042
Patrick W. Gallagher is an academic researcher. The author has contributed to research in topics: Convolutional neural network & MNIST database. The author has an hindex of 4, co-authored 5 publications receiving 2702 citations.
Papers
More filters
Proceedings Article
Deeply-Supervised Nets
TL;DR: Deeply-supervised nets (DSN) as discussed by the authors is a method that simultaneously minimizes classication error and improves the directness and transparency of the hidden layer learning process by introducing companion objective functions at each hidden layer, in addition to the overall objective function at the output layer.
Posted Content
Deeply-Supervised Nets
TL;DR: Deeply-supervised nets (DSN) as discussed by the authors proposes a companion objective to the individual hidden layers, in addition to the overall objective at the output layer, which is a different strategy to layer-wise pre-training.
Posted Content
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
TL;DR: In this article, the authors propose to learn a pooling function via combining of max and average pooling, and then combine them in a tree-structured fusion of pooling filters that are themselves learned.
Proceedings Article
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
TL;DR: The proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets; they are also easy to implement, and can be applied within various deep neural network architectures.
Posted Content
Properties of Pseudocontractive Updates in Convex Optimization
Patrick W. Gallagher,Zhuowen Tu +1 more
TL;DR: This manuscript demonstrates the utility of an important but largely unremarked common thread running through many prominent optimization methods, and proves a novel bound satisfied by the norm of the difference in iterates of pseudocontractive updates.