An Introduction to Neural Architecture Search for Convolutional Networks

Kyriakides, George; Margaritis, Konstantinos

doi:10.48550/arxiv.2005.11074

Cited by 9 publications

(8 citation statements)

References 24 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It remains to be explored by using more advanced network structures, e.g., vision transformer [37] for medical image classification tasks in the context of DAM. Another interesting direction is to explore neural architecture search (NAS) [82] in the context of DAM. A natural question is if we use AUC as a performance measure of NAS, how would the found network be different from standard approaches that use accuracy as a performance measure.…”

Section: Other Issues For Dam and Outlook For Future Workmentioning

confidence: 99%

AUC Maximization in the Era of Big Data and AI: A Survey

Yang¹,

Ying²

2022

Preprint

View full text Add to dashboard Cite

Area under the ROC curve, a.k.a. AUC, is a measure of choice for assessing the performance of a classifier for imbalanced data. AUC maximization refers to a learning paradigm that learns a predictive model by directly maximizing its AUC score. It has been studied for more than two decades dating back to late 90s and a huge amount of work has been devoted to AUC maximization since then. Recently, stochastic AUC maximization for big data and deep AUC maximization for deep learning have received increasing attention and yielded great impact for solving real-world problems. However, to the best our knowledge there is no comprehensive survey of related works for AUC maximization. This paper aims to address the gap by reviewing the literature in the past two decades. We not only give a holistic view of the literature but also present detailed explanations and comparisons of different papers from formulations to algorithms and theoretical guarantees. We also identify and discuss remaining and emerging issues for deep AUC maximization, and provide suggestions on topics for future work.

show abstract

Section: Other Issues For Dam and Outlook For Future Workmentioning

confidence: 99%

AUC Maximization in the Era of Big Data and AI: A Survey

Yang¹,

Ying²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Neural Architecture Search (NAS) refers to the automated process of neural architectural design [88]. It has been largely successful in producing many state-of-the-art networks.…”

Section: Hardware-aware Neural Architecture Search (Nas)mentioning

confidence: 99%

Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems

Zhang¹,

Chen²,

Hao³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…The third class uses RL to train a network-generating agent that generates model description to maximize reward function [34]. A survey [35] discusses the pros and cons of each class. Our work uses a differentiable approach to obtain a high performing Q-learning model in the RL setting for robotic manipulation tasks.…”

Section: Related Workmentioning

confidence: 99%

Visionary: Vision architecture discovery for robot learning

Akinola¹,

Angelova²,

Lu³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs. Our approach automatically designs architectures while training on the task -discovering novel ways of combining and attending image feature representations with actions as well as features from previous layers. The obtained new architectures demonstrate better task success rates, in some cases with a large margin, compared to a recent high performing baseline. Our real robot experiments also confirm that it improves grasping performance by 6%. This is the first approach to demonstrate a successful neural architecture search and attention connectivity search for a real-robot task.

show abstract

An Introduction to Neural Architecture Search for Convolutional Networks

Cited by 9 publications

References 24 publications

AUC Maximization in the Era of Big Data and AI: A Survey

AUC Maximization in the Era of Big Data and AI: A Survey

Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems

Visionary: Vision architecture discovery for robot learning

Contact Info

Product

Resources

About