English
Related papers

Related papers: PEng4NN: An Accurate Performance Estimation Engine…

200 papers

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all…

Computer Vision and Pattern Recognition · Computer Science 2019-05-30 Mingxing Tan , Bo Chen , Ruoming Pang , Vijay Vasudevan , Mark Sandler , Andrew Howard , Quoc V. Le

Neural architecture search (NAS) has shown promising results discovering models that are both accurate and fast. For NAS, training a one-shot model has become a popular strategy to rank the relative quality of different architectures (child…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Jiahui Yu , Pengchong Jin , Hanxiao Liu , Gabriel Bender , Pieter-Jan Kindermans , Mingxing Tan , Thomas Huang , Xiaodan Song , Ruoming Pang , Quoc Le

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search for each deployment specification of hardware or objective.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Zhichao Lu , Gautam Sreekumar , Erik Goodman , Wolfgang Banzhaf , Kalyanmoy Deb , Vishnu Naresh Boddeti

Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. Despite these high expectation, the effectiveness and…

Computer Vision and Pattern Recognition · Computer Science 2020-03-09 Changlin Li , Jiefeng Peng , Liuchun Yuan , Guangrun Wang , Xiaodan Liang , Liang Lin , Xiaojun Chang

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

Machine Learning · Computer Science 2020-09-29 Xinyue Zheng , Peng Wang , Qigang Wang , Zhongchao Shi

Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation. To address this issue, instead of using an accuracy…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Ming Lin , Pichao Wang , Zhenhong Sun , Hesen Chen , Xiuyu Sun , Qi Qian , Hao Li , Rong Jin

Neural Architecture Search (NAS) algorithms aim at finding efficient Deep Neural Network (DNN) architectures for a given application under given system constraints. DNNs are computationally-complex as well as vulnerable to adversarial…

Machine Learning · Computer Science 2025-10-23 Alberto Marchisio , Vojtech Mrazek , Andrea Massa , Beatrice Bussolino , Maurizio Martina , Muhammad Shafique

Many mission-critical systems are based on GPU for inference. It requires not only high recognition accuracy but also low latency in responding time. Although many studies are devoted to optimizing the structure of deep models for efficient…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Ming Lin , Hesen Chen , Xiuyu Sun , Qi Qian , Hao Li , Rong Jin

The benchmark datasets for neural architecture search (NAS) have been developed to alleviate the computationally expensive evaluation process and ensure a fair comparison. Recent NAS benchmarks only focus on architecture optimization,…

Machine Learning · Computer Science 2021-10-22 Yoichi Hirose , Nozomu Yoshinari , Shinichi Shirakawa

Neural architecture search (NAS) has allowed for the automatic creation of new and effective neural network architectures, offering an alternative to the laborious process of manually designing complex architectures. However, traditional…

Machine Learning · Computer Science 2023-06-02 Aaron Serianni , Jugal Kalita

Neural architecture search (NAS) enables researchers to automatically explore broad design spaces in order to improve efficiency of neural networks. This efficiency is especially important in the case of on-device deployment, where…

Machine Learning · Computer Science 2021-01-20 Łukasz Dudziak , Thomas Chau , Mohamed S. Abdelfattah , Royson Lee , Hyeji Kim , Nicholas D. Lane

Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation. In forward modeling problems, PINNs are meshless partial…

Machine Learning · Computer Science 2023-11-28 Yicheng Wang , Xiaotian Han , Chia-Yuan Chang , Daochen Zha , Ulisses Braga-Neto , Xia Hu

Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search…

Computer Vision and Pattern Recognition · Computer Science 2022-04-28 Yameng Peng , Andy Song , Vic Ciesielski , Haytham M. Fayek , Xiaojun Chang

Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult…

Machine Learning · Computer Science 2019-02-26 Han Cai , Ligeng Zhu , Song Han

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim…

Machine Learning · Computer Science 2019-05-15 Chris Ying , Aaron Klein , Esteban Real , Eric Christiansen , Kevin Murphy , Frank Hutter

In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. Due to the high computational costs, most recent approaches to NAS as well as the few…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Jovita Lukasik , David Friede , Heiner Stuckenschmidt , Margret Keuper

Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can…

Machine Learning · Computer Science 2017-11-09 Bowen Baker , Otkrist Gupta , Ramesh Raskar , Nikhil Naik

Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture…

Neural and Evolutionary Computing · Computer Science 2019-04-02 Gerard Jacques van Wyk , Anna Sergeevna Bosman

The ongoing advancements in network architecture design have led to remarkable achievements in deep learning across various challenging computer vision tasks. Meanwhile, the development of neural architecture search (NAS) has provided…

Neural and Evolutionary Computing · Computer Science 2023-04-19 Zhichao Lu , Ran Cheng , Yaochu Jin , Kay Chen Tan , Kalyanmoy Deb

Graph neural networks (GNNs) have emerged as a popular strategy for handling non-Euclidean data due to their state-of-the-art performance. However, most of the current GNN model designs mainly focus on task accuracy, lacking in considering…

Machine Learning · Computer Science 2023-04-14 Ao Zhou , Jianlei Yang , Yingjie Qi , Yumeng Shi , Tong Qiao , Weisheng Zhao , Chunming Hu