Robust Optimization of Convolution Natural Network

Deep learning has played a very important role in computer vision. However, most of the methods used in computer vision highly rely on human to adjust the hyperparameter. That takes researchers lots of time, but the results sometime could not be most optimized. Besides, many architectures cannot per...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2020-10, Vol.1650 (3), p.32105
Main Author: Ye, Chongjie
Format: Article
Language:English
Subjects:
Algorithms
Computer vision
Convolution
Convolutional Neural Networks
Fruit Fly Optimization
Machine learning
Noise
Optimization
Physics
Robust
Robustness
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning has played a very important role in computer vision. However, most of the methods used in computer vision highly rely on human to adjust the hyperparameter. That takes researchers lots of time, but the results sometime could not be most optimized. Besides, many architectures cannot perform robustly in training with noised data. This essay aims to solve the hyperparameter optimization problem by adapting the fruit fly optimization algorithm and suppose a high robust Convolution Natural Network including a Gaussian filter. Compared with methods such as FaceNe, InceptionV3 and Resnet5, GauCNN perform higher efficiency and accuracy with noise data.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1650/3/032105