activity
20082023
most citedAdaptive Loss Scaling for Mixed Precision Training

6 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2023

An NMF-Based Building Block for Interpretable Neural Networks With Continual Learning

Brian K. Vogel

Existing learning methods often struggle to balance interpretability and predictive performance. While models like nearest neighbors and non-negative matrix factorization (NMF) off…

cs.LG20191 cited

Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling

Daniel Stoller, Mi Tian, Sebastian Ewert +1

Convolutional neural networks (CNNs) with dilated filters such as the Wavenet or the Temporal Convolutional Network (TCN) have shown good results in a variety of sequence modelling…

cs.LG20196 cited

Adaptive Loss Scaling for Mixed Precision Training

Ruizhe Zhao, Brian Vogel, Tanvir Ahmed

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support…

cs.LG2019

Chainer: A Deep Learning Framework for Accelerating the Research Cycle

Seiya Tokui, Ryosuke Okuta, Takuya Akiba +7

Software frameworks for neural networks play a key role in the development and application of deep learning methods. In this paper, we introduce the Chainer framework, which intend…

cs.LG2008

Positive factor networks: A graphical framework for modeling non-negative sequential data

Brian K. Vogel

We present a novel graphical framework for modeling non-negative sequential data with hierarchical structure. Our model corresponds to a network of coupled non-negative matrix fact…