Deep Hybrid Real-Complex-Valued Convolutional Neural Networks for Image Classification

机译：用于图像分类的深混合实值复卷积神经网络

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Shallow complex-valued convolutional neural networks (CVCNNs) have displayed better performance than their real-valued counterparts (RVCNNs). This paper presents a deep CVCNN architecture inspired by the well known VGG architecture. The different structure of learning in the complex domain compared with the real domain means that CVCNNs make systematically different errors than RVCNNs. This led to the idea of a hybrid real-complex-valued ensemble of the two types of networks, which combines the advantages of both. Experiments done on the SVHN, CIFAR-10, and CIFAR- 100 datasets show better results of the CVCNNs compared with RVCNNs, and significantly better results of the hybrid real-complex-valued ensemble compared with both types of networks.

机译：浅层复数值卷积神经网络（CVCNN）的性能优于其实际值对应的卷积神经网络（RVCNN）。本文提出了一种深层的CVCNN架构，其灵感来自于著名的VGG架构。与真实域相比，复杂域中的学习结构不同，这意味着CVCNN与RVCNN相比在系统上会产生不同的错误。这导致了将两种类型的网络混合为实复值集合的想法，该方法结合了两者的优点。在SVHN，CIFAR-10和CIFAR-100数据集上进行的实验表明，与RVCNN相比，CVCNN的结果更好，与两种类型的网络相比，混合实数-复杂值集成的结果也明显更好。

著录项

来源
《International Joint Conference on Neural Networks》|2018年|1-6|共6页
会议地点
作者
Călin-Adrian Popa;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Convolution; Convolutional neural networks; Image recognition; Machine learning; Synthetic aperture radar; Kernel;

机译：卷积;卷积神经网络;图像识别;机器学习;合成孔径雷达;核;

相似文献

外文文献
中文文献
专利

1. 基于实复值混合时延神经网络的宽带功放的建模和线性化 [J] . 惠明, 张新刚, 张萌, 东南大学学报（英文版） . 2018,第002期
2. Hybrid classification of diffuse liver diseases in ultrasound images using deep convolutional neural networks [J] . Pezhman Pasyar, Tahereh Mahmoudi, Seyedeh-Zahra Mousavi Kouzehkanan, Informatics in Medicine Unlocked . 2021,第a期

机译：利用深卷积神经网络杂交肝病弥漫性肝病的杂化分类
3. Unsupervised Land Cover Classification of Hybrid and Dual-Polarized Images Using Deep Convolutional Neural Network [J] . Chatterjee Ankita, Saha Jayasree, Mukherjee Jayanta, IEEE Geoscience and Remote Sensing Letters . 2021,第6期

机译：使用深卷积神经网络的无监督土地覆盖混合和双极化图像的分类
4. Detection and classification of lung nodules in chest X-ray images using deep convolutional neural networks [J] . Julio Mendoza, Helio Pedrini Computational Intelligence . 2020,第2期

机译：利用深卷积神经网络检测和分类胸X射线图像中的肺结节
5. Deep Hybrid Real-Complex-Valued Convolutional Neural Networks for Image Classification [C] . C?lin-Adrian Popa International Joint Conference on Neural Networks . 2018

机译：用于图像分类的深杂交真正复合值卷积神经网络
6. Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks [D] . Hassan, Abdalraouf. 2018

机译：基于卷积神经网络和递归神经网络的深度神经语言文本分类模型
7. Automated Pulmonary Nodule Classification in Computed Tomography Images Using a Deep Convolutional Neural Network Trained by Generative Adversarial Networks [O] . Yuya Onishi, Atsushi Teramoto, Masakazu Tsujimoto, 2006

机译：使用由生成对抗网络训练的深卷积神经网络在计算机断层扫描图像中自动进行肺结节分类
8. Classification of Pulmonary CT Images by Using Hybrid 3D-Deep Convolutional Neural Network Architecture [O] . Huseyin Polat, Homay Danaei Mehr 2019

机译：使用混合3D深卷积神经网络架构进行肺CT图像的分类

Deep Hybrid Real-Complex-Valued Convolutional Neural Networks for Image Classification

摘要

著录项

相似文献

相关主题

期刊订阅