.png){kind=icon}
返回
Automating Configuration of Convolutional Neural Network Hyperparameters Using Genetic Algorithm
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.3019245.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, Convolutional Neural Networks (CNN) have been widely used for real-world applications in the field of computer vision. Their class-leading performance, however, depends heavily on the architecture used for a given problem. In most cases, the architectures are manually optimized by the researchers, a time-consuming process hard to achieve without prior knowledge of CNN. In this paper, we propose a new genetic algorithm for the optimization of the CNN architecture for a given image classification problem. This algorithm extends and refines existing research in the field, by allowing depth exploration, introducing a novel sequential crossover operator, using an incremental selective pressure schedule over evolution (favoring higher diversity in early generations) and by evaluating individual performances over the validation set with early stopping. The technique is validated in three image classification dataset, namely, CIFAR10, MNIST and Caltech256 datasets, which are widely used benchmarks for image classification algorithms. We evaluate the performance and total execution time over these datasets, and compare our results with those achieved by the best genetic methods published so far. In all cases, we achieve better results in terms of test accuracy, consistently over different datasets, while remaining in the same orders of magnitude of execution time of the fastest approaches.
Keyword:
Optimization
Genetic algorithms
Prediction algorithms
Computer architecture
Task analysis
Kernel
Training
Artificial neural network
genetic algorithm
image classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
HDAC4 stimulates MRTF-A expression and drives fibrogenesis in hepatic stellate cells by targeting miR-206.png)
Oncotarget
OAAI
OncotargetIF0
OAAI分享收藏Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram基于心电图谱图模式的阻塞性睡眠呼吸暂停分类
PREAI
分享收藏Long-Term Monitoring of Field Trial Sites with Genetically Modified Oilseed Rape (Brassica napus L.) in Saxony-Anhalt, Germany. Fifteen Years Persistence to Date but No Spatial DispersionGenesOAAI
GenesIF0
OAAI分享收藏分享收藏Investigation of Ti mesh-supported anodes for direct borohydride fuel cells直接硼氢化物燃料电池用钛网支撑阳极的研究
PREAI
分享收藏
查看更多内容