☆ 4.7 Article

LoNAS: Low-Cost Neural Architecture Search Using a Three-Stage Evolutionary Algorithm

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Evolutionary convolutional neural network for image classification based on multi-objective genetic programming with leader-follower mechanism

Qingqing Liu et al.

Summary: This article proposes a multi-objective genetic programming algorithm with a leader-follower evolution mechanism (LF-MOGP) to represent the topology of CNNs using a flexible encoding strategy with variable length and width. The LF-MOGP algorithm increases the speed of population convergence, ensures the diversity of individuals, and reduces computational resources.

COMPLEX & INTELLIGENT SYSTEMS (2023)

添加到收藏夹

Article Environmental Sciences

Early Prediction of Sepsis Onset Using Neural Architecture Search Based on Genetic Algorithms

Jae Kwan Kim et al.

Summary: This paper proposes a neural architecture search (NAS) model using a genetic algorithm (GA) to predict the onset of sepsis. The model achieves low computational cost and high search performance by sharing weights internally within the neural network and reducing search cost through weight-sharing between GA genotypes. The model outperforms traditional scoring systems and other models in predicting sepsis onset, with a high AUROC score of 0.94 for 3 hours.

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

AS-NAS: Adaptive Scalable Neural Architecture Search With Reinforced Evolutionary Algorithm for Deep Learning

Tong Zhang et al.

Summary: The AS-NAS method proposes an adaptive and scalable NAS approach that enhances search efficiency and achieves scalability of deep neural architecture through a simplified RL algorithm and variable-architecture encoding strategy.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

添加到收藏夹

Article Computer Science, Information Systems

SP-DARTS: Synchronous Progressive Differentiable Neural Architecture Search for Image Classification

Zimin Zhao et al.

Summary: This paper proposes a synchronous progressive approach to solve the discontinuity problem of network depth and width, using 0-1 loss function to alleviate the discontinuity issue and reduce computational overhead.

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition

Ming Lin et al.

Summary: This paper introduces a new zero-shot index called Zen-Score to rank neural networks, which reflects the positive correlation between network expressivity and model accuracy. Based on Zen-Score, a new NAS algorithm named Zen-NAS is proposed, which can directly search high-performance architectures in less than half a day of GPU time.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator

Sian-Yao Huang et al.

Summary: The study introduces a novel search strategy called architecture generator to efficiently and flexibly search for sub-networks. With the architecture generator and unified supernet, a flexible and efficient one-shot NAS framework is proposed.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

An Efficient and Flexible Automatic Search Algorithm for Convolution Network Architectures

Liang Zhao et al.

Summary: An efficient and flexible CNN architecture search algorithm (EF-CNN) is proposed in this paper, which constructs a flexible search space by considering depth, width, and lightweight blocks, and introduces a multi-objective fitness correction method. Experimental results show that the CNN architecture designed by EF-CNN is highly competitive in performance while significantly reducing computational time.

2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

EVSRNet: Efficient Video Super-Resolution with Neural Architecture Search

Shaoli Liu et al.

Summary: This study introduces an Efficient Video Super-Resolution Network (EVSRNet) with neural architecture search for real-time video super-resolution, demonstrating a good balance between quality and efficiency. The method achieved competitive results in the Mobile AI 2021 real-time video super-resolution challenge, being the fastest and significantly outperforming other competitors.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Evolving Deep Convolutional Neural Networks for Image Classification

Yanan Sun et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Completely Automated CNN Architecture Design Based on Blocks

Yanan Sun et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

添加到收藏夹

Article Automation & Control Systems

Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification

Yanan Sun et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm

Zhichao Lu et al.

PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19) (2019)

添加到收藏夹

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks

Chunshui Cao et al.

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Differential evolution algorithm with ensemble of parameters and mutation strategies

R. Mallipeddi et al.

APPLIED SOFT COMPUTING (2011)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.