Differential convolutional neural network

卷积神经网络 卷积(计算机科学) 计算机科学 人工智能 模式识别(心理学) 算法 深度学习 集合(抽象数据类型) 特征(语言学) 反向传播 人工神经网络 语言学 哲学 程序设计语言
作者
Mehmet Sarıgül,Buse Melis Özyıldırım,Mutlu Avcı
出处
期刊:Neural Networks [Elsevier BV]
卷期号:116: 279-287 被引量:147
标识
DOI:10.1016/j.neunet.2019.04.025
摘要

Convolutional neural networks with strong representation ability of deep structures have ever increasing popularity in many research areas. The main difference of Convolutional Neural Networks with respect to existing similar artificial neural networks is the inclusion of the convolutional part. This inclusion directly increases the performance of artificial neural networks. This fact has led to the development of many different convolutional models and techniques. In this work, a novel convolution technique named as Differential Convolution and updated error back-propagation algorithm is proposed. The proposed technique aims to transfer feature maps containing directional activation differences to the next layer. This implementation takes the idea of how convolved features change on the feature map into consideration. In a sense, this process adapts the mathematical differentiation operation into the convolutional process. Proposed improved back propagation algorithm also considers neighborhood activation errors. This property increases the classification performance without changing the number of filters. Four different experiment sets were performed to observe the performance and the adaptability of the differential convolution technique. In the first experiment set utilization of the differential convolution on a traditional convolutional neural network structure made a performance boost up to 55.29% for the test accuracy. In the second experiment set differential convolution adaptation raised the top1 and top5 test accuracies of AlexNet by 5.3% and 4.75% on ImageNet dataset. In the third experiment set differential convolution utilized model outperformed all compared convolutional structures. In the fourth experiment set, the Differential VGGNet model obtained by adapting proposed differential convolution technique performed 93.58% and 75.06% accuracy values for CIFAR10 and CIFAR100 datasets, respectively. The accuracy values of the Differential NIN model containing differential convolution operation were 92.44% and 72.65% for the same datasets. In these experiment sets, it was observed that the differential convolution technique outperformed both traditional convolution and other compared convolution techniques. In addition, easy adaptation of the proposed technique to different convolutional structures and its efficiency demonstrate that popular deep learning models may be improved with differential convolution.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
FashionBoy的应助被苍耳采纳,获得50
1秒前
orixero的应助被lzqsg采纳,获得10
1秒前
1秒前
3秒前
纾寒发布了新的文献求助10
3秒前
777关注了科研通微信公众号
4秒前
自由寻梅发布了新的文献求助10
4秒前
小羊完成签到 ,获得积分10
5秒前
科研通AI6.4的应助被liuguagxiyv采纳,获得10
7秒前
shenkekeshen的应助被wcc采纳,获得10
8秒前
mmm完成签到,获得积分10
8秒前
英姑的应助被皮皮采纳,获得10
8秒前
科研通AI65的应助被初景采纳,获得10
8秒前
学霸业的应助被原神大王采纳,获得10
8秒前
8秒前
CipherSage的应助被yjt采纳,获得10
9秒前
pluto的应助被娇娇尚采纳,获得10
11秒前
11秒前
菜虫虫完成签到,获得积分10
13秒前
邱邱科研发布了新的文献求助10
14秒前
mymy完成签到,获得积分10
14秒前
14秒前
科研通AI6.4的应助被西柏采纳,获得10
14秒前
15秒前
自由寻梅完成签到,获得积分20
15秒前
Twinkle发布了新的文献求助10
15秒前
今天我写论文了吗关注了科研通微信公众号
16秒前
17秒前
17秒前
张书源完成签到,获得积分10
17秒前
yjt发布了新的文献求助10
21秒前
桐桐的应助被虚心十三采纳,获得10
22秒前
一月平芜发布了新的文献求助10
22秒前
张书源发布了新的文献求助10
23秒前
zhouyi完成签到,获得积分10
23秒前
23秒前
jiangnantingyu完成签到 ,获得积分20
24秒前
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8189472
求助须知:如何正确求助?哪些是违规求助? 9576774
关于积分的说明 21849709
捐赠科研通 7787422
什么是DOI,文献DOI怎么找? 3435600
关于科研通互助平台的介绍 2559782
邀请新用户注册赠送积分活动 2482552