activity
20172020
most citedExploring loss function topology with cyclical learning rates

18 citations · 20 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2020

FROST: Faster and more Robust One-shot Semi-supervised Training

Helena E. Liu, Leslie N. Smith

Recent advances in one-shot semi-supervised learning have lowered the barrier for deep learning of new applications. However, the state-of-the-art for semi-supervised learning is s…

cs.LG2020

Building One-Shot Semi-supervised (BOSS) Learning up to Fully Supervised Performance

Leslie N. Smith, Adam Conovaloff

Reaching the performance of fully supervised learning with unlabeled data and only labeling one sample per class might be ideal for deep learning applications. We demonstrate for t…

cs.LG20201 cited

Empirical Perspectives on One-Shot Semi-supervised Learning

Leslie N. Smith, Adam Conovaloff

One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled traini…

cs.LG20191 cited

A Useful Taxonomy for Adversarial Robustness of Neural Networks

Leslie N. Smith

Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories;…

cs.LG2018

A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

Leslie N. Smith

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-param…

cs.LG201718 cited

Exploring loss function topology with cyclical learning rates

Leslie N. Smith, Nicholay Topin

We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of n…