Filters








5,102 Hits in 5.1 sec

Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search [article]

Xiangxiang Chu and Bo Zhang and Ruijun Xu and Hailong Ma
2019 arXiv   pre-print
In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and  ...  Both evolution algorithms (EA) and reinforced learning methods (RL) have been dedicated to solve neural architecture search problems.  ...  To sum up, our method Conclusion In this paper, we propose a multi-objective reinforced evolution algorithm in mobile neural architecture search, which seeks a better trade-off among various competing  ... 
arXiv:1901.01074v3 fatcat:7muct2dfp5bzreymyxk3ddv2ni

Searching Toward Pareto-Optimal Device-Aware Neural Architectures [article]

An-Chieh Cheng, Jin-Dong Dong, Chi-Hung Hsu, Shu-Huan Chang, Min Sun, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan
2018 arXiv   pre-print
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding.  ...  Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded  ...  Multi-objective Neural Architecture Search Most existing methods focus only on optimizing a single objective: model accuracy.  ... 
arXiv:1808.09830v2 fatcat:423unviiuzabhdxnkwhaglt64m

MnasNet: Platform-Aware Neural Architecture Search for Mobile [article]

Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, Quoc V. Le
2019 arXiv   pre-print
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that  ...  Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate.  ...  We introduce a multi-objective neural architecture search approach that optimizes both accuracy and realworld latency on mobile devices. 2.  ... 
arXiv:1807.11626v3 fatcat:zhtycexwfnd2lopcq2pmgsukju

RC-DARTS: Resource Constrained Differentiable Architecture Search [article]

Xiaojie Jin, Jiang Wang, Joshua Slocum, Ming-Hsuan Yang, Shengyang Dai, Shuicheng Yan, Jiashi Feng
2019 arXiv   pre-print
We also propose a multi-level search strategy to enable layers at different depths to adaptively learn different types of neural architectures.  ...  Recent advances show that Neural Architectural Search (NAS) method is able to find state-of-the-art image classification deep architectures.  ...  [19] proposed to treat neural network architecture search as a multi-objective optimization task and adopt an evolutionary algorithm to search models with two objectives, run-time speed, and classification  ... 
arXiv:1912.12814v1 fatcat:k2s2lyy7arb4zfxktildn7lssa

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, Quoc V. Le
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that  ...  Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate.  ...  We introduce a multi-objective neural architecture search approach that optimizes both accuracy and realworld latency on mobile devices. 2.  ... 
doi:10.1109/cvpr.2019.00293 dblp:conf/cvpr/TanCPVSHL19 fatcat:fnvmm4cnnve3jbc2nd23qljr2a

Reinforced Evolutionary Neural Architecture Search [article]

Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, Xinggang Wang
2019 arXiv   pre-print
Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption.  ...  Our method integrates reinforced mutation into an evolution algorithm for neural architecture exploration, in which a mutation controller is introduced to learn the effects of slight modifications and  ...  In this paper, we propose the Reinforced Evolutionary Neural Architecture Search (RENAS), which integrates RL into the evolution framework to address the above issues.  ... 
arXiv:1808.00193v3 fatcat:auuxuabazrh5xmkrx4k5ktpz2e

RENAS: Reinforced Evolutionary Neural Architecture Search

Yukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, Xinggang Wang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption.  ...  Our method integrates reinforced mutation into an evolution algorithm for neural architecture exploration, in which a mutation controller is introduced to learn the effects of slight modifications and  ...  In this paper, we propose the Reinforced Evolutionary Neural Architecture Search (RENAS), which integrates RL into the evolution framework to address the above issues.  ... 
doi:10.1109/cvpr.2019.00492 dblp:conf/cvpr/ChenMZXHMW19 fatcat:3xkal6bp7vdzxcj4uj224q6vri

TND-NAS: Towards Non-Differentiable Objectives in Differentiable Neural Architecture Search [article]

Bo Lyu, Shiping Wen, Zheng Yan, Kaibo Shi, Ke Li, Tingwen Huang
2022 arXiv   pre-print
Differentiable architecture search has gradually become the mainstream research topic in the field of Neural Architecture Search (NAS) for its high efficiency compared with the early NAS (EA-based, RL-based  ...  Researches in the multi-objective NAS field target this but requires vast computational resources cause of the sole optimization of each candidate architecture.  ...  searching for the neural architectures in discrete space with the consideration of multi-dimensional metrics, including differentiable and non-differentiable ones.  ... 
arXiv:2111.03892v2 fatcat:wgn45wznjvcntp6evov4so25gm

DVOLVER: Efficient Pareto-Optimal Neural Network Architecture Search [article]

Guillaume Michel, Mohammed Amine Alaoui, Alice Lebois, Amal Feriani, Mehdi Felhi
2019 arXiv   pre-print
In this paper, we present a multi-objective neural architecture search method to find a family of CNN models with the best accuracy and computational resources tradeoffs, in a search space inspired by  ...  the state-of-the-art findings in neural search.  ...  In this article, we introduce Dvolver, a principled multi-objective neural architecture search approach using Pareto optimality to navigate the search space.  ... 
arXiv:1902.01654v1 fatcat:r7podmzsdzgqbjse3c7dfv36re

Joint Neural Architecture Search and Quantization [article]

Yukang Chen, Gaofeng Meng, Qian Zhang, Xinbang Zhang, Liangchen Song, Shiming Xiang, Chunhong Pan
2018 arXiv   pre-print
Technically, a multi-objective evolutionary search algorithm is introduced to search the models under the balance between model size and performance accuracy.  ...  Designing neural architectures is a fundamental step in deep learning applications.  ...  In this paper, we define the search problem as a multi-objective problem.  ... 
arXiv:1811.09426v1 fatcat:jj5kspr46zbknjysobfvnnmnui

Effective, Efficient and Robust Neural Architecture Search [article]

Zhixiong Yue, Baijiong Lin, Xiaonan Huang, Yu Zhang
2020 arXiv   pre-print
Recent advances in adversarial attacks show the vulnerability of deep neural networks searched by Neural Architecture Search (NAS).  ...  To solve this problem, we propose an Effective, Efficient, and Robust Neural Architecture Search (E2RNAS) method to search a neural network architecture by taking the performance, robustness, and resource  ...  Therefore, Neural Architecture Search (NAS), which aims to design the architecture of neural networks in an automated way, has attracted great attentions in recent years.  ... 
arXiv:2011.09820v1 fatcat:2dc3ccqivjc63pbucg5fj7obyi

CARS: Continuous Evolution for Efficient Neural Architecture Search [article]

Zhaohui Yang, Yunhe Wang, Xinghao Chen, Boxin Shi, Chao Xu, Chunjing Xu, Qi Tian, Chang Xu
2020 arXiv   pre-print
Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason.  ...  In contrast, we develop an efficient continuous evolutionary approach for searching neural networks.  ...  Techniques for searching neural architectures are mainly clustered into three groups, i.e., Evolution Algorithm (EA) based, Reinforcement Learning (RL) based, and gradientbased methods.  ... 
arXiv:1909.04977v6 fatcat:r53hs6hgjfct3gmglq4j4l66vy

Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution [article]

Thomas Elsken, Jan Hendrik Metzen, Frank Hutter
2019 arXiv   pre-print
Neural Architecture Search aims at automatically finding neural architectures that are competitive with architectures designed by human experts.  ...  We address the first shortcoming by proposing LEMONADE, an evolutionary algorithm for multi-objective architecture search that allows approximating the entire Pareto-front of architectures under multiple  ...  Multi-objective Neural Architecture Search Very recently, there has also been some work on multi-objective neural architecture search (Kim et al., 2017; Dong et al., 2018; Tan et al., 2018) with the  ... 
arXiv:1804.09081v4 fatcat:5suu2qsh45a7vfwifjz743zpoq

PATH FINDING BASED ON ARTIFICIAL INTELLIGENCE TECHNIQUES: A REVIEW

Dr. Eyad I. Abbas, Dr. Sundus D. Hasan, Rawaa Jawad
2020 International Journal of Engineering Applied Sciences and Technology  
Path finding reduce the wear and capital investment of mobile robot. Several methodologies have been proposed and reported in the literature for the path planning of mobile robot.  ...  Although these methodologies do not guarantee an optimal solution, they have been successfully applied in their works.  ...  Solving the Path Planning Problem in Mobile Robotics with the Multi-Objective Evolutionary Algorithm Yang Xue et.al.  ... 
doi:10.33564/ijeast.2020.v05i04.013 fatcat:6ayyqxh5enbrplfunh5vkx2vva

Table of Contents

2020 2020 IEEE Symposium Series on Computational Intelligence (SSCI)  
: Learning from Neural Architecture Search Bas van Stein, Hao Wang and Thomas Back .......... 1341 CIDUE2: Learning in Non-Stationary and Uncertain Environments/Dynamic Single and Multi-Objective Optimization  ...  Eiben .......... 2272 ENASA1: Neuroevolution/Neural Architecture Design, Chair: Yanan Sun Objective Comparison and Selection in Mono-and Multi-Objective Evolutionary Neurocontrollers Ian Showalter  ... 
doi:10.1109/ssci47803.2020.9308155 fatcat:hyargfnk4vevpnooatlovxm4li
« Previous Showing results 1 — 15 out of 5,102 results