Results 21 to 30 of about 6,198,210 (289)

RARTS: An Efficient First-Order Relaxed Architecture Search Method

IEEE Access, 2022
Differentiable architecture search (DARTS) is an effective method for data-driven neural network design based on solving a bilevel optimization problem.
Fanghui Xue, Yingyong Qi, Jack Xin
doaj   +1 more source

Advances in neural architecture search. [PDF]

Natl Sci Rev
ABSTRACT Automated machine learning (AutoML) has achieved remarkable success in automating the non-trivial process of designing machine learning models. Among the focal areas of AutoML, neural architecture search (NAS) stands out, aiming to systematically explore the complex architecture space to discover the optimal neural ...
Wang X, Zhu W.
europepmc   +3 more sources

Neural Architecture Search with Random Labels [PDF]

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS). The task sounds counter-intuitive for most existing NAS algorithms since random label provides few information on the performance of each candidate architecture.
Xuanyang Zhang, Pengfei Hou, Xiangyu Zhang 0005, Jian Sun 0001   +3 more
openaire   +2 more sources

Neural Architecture Search and Hardware Accelerator Co-Search: A Survey

IEEE Access, 2021
Deep neural networks (DNN) are now dominating in the most challenging applications of machine learning. As DNNs can have complex architectures with millions of trainable parameters (the so-called weights), their design and training are difficult even for
Lukas Sekanina
doaj   +1 more source

Evolving Search Space for Neural Architecture Search [PDF]

2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Accepted for publication at the 2021 International Conference on Computer Vision (ICCV 2021)
Yuanzheng Ci, Chen Lin 0003, Ming Sun 0008, Boyu Chen, Hongwen Zhang 0001, Wanli Ouyang   +5 more
openaire   +2 more sources

A Fast and Progressive Convolutional Neural Architecture Search Algorithm [PDF]

Jisuanji gongcheng, 2022
Manually designing a Convolutional Neural Network(CNN) architecture is extremely difficult and requires a high level of professionalism.The gradient differentiable search is fast and efficient.However, this method has some drawbacks, such as a large gap ...
ZHAO Liang, FANG Wei
doaj   +1 more source

Neural Architecture Search Benchmarks: Insights and Survey

IEEE Access, 2023
Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset.
Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath, Arun K. Somani   +3 more
doaj   +1 more source

Neural Architecture Search for Inversion

CoRR, 2022
Over the year, people have been using deep learning to tackle inversion problems, and we see the framework has been applied to build relationship between recording wavefield and velocity (Yang et al., 2016). Here we will extend the work from 2 perspectives, one is deriving a more appropriate loss function, as we now, pixel-2-pixel comparison might not ...
Cheng Zhan, Licheng Zhang, Xin Zhao, Chang-Chun Lee, Shujiao Huang   +4 more
openaire   +2 more sources

One-Shot Neural architecture search via novelty driven sampling [PDF]

, 2020
One-Shot Neural architecture search (NAS) has received wide attentions due to its computational efficiency. Most state-of-the-art One-Shot NAS methods use the validation accuracy based on inheriting weights from the supernet as the stepping stone to ...
Zhang, Miao, Taoping Liu, Shirui Pan, Li, Huiqi, Su, Steven, Pan, Shirui, Miao Zhang, Huiqi Li, Steven Su, Liu, Taoping, Liu, T, Li, H, Pan, S, Zhang, M, Su, S   +14 more
core   +1 more source

Neural Architecture Search: A Survey

J. Mach. Learn. Res., 2018
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error ...
Elsken, Thomas, Metzen, Jan Hendrik, Hutter, Frank   +2 more
openaire   +5 more sources