IEICE Transactions on Information and Systems最新文献_第10页

Feedback Node Sets in Pancake Graphs and Burnt Pancake Graphs 煎饼图和烧焦煎饼图中的反馈节点集

4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-10-01 DOI: 10.1587/transinf.2022edp7211

Sinyu JUNG, Keiichi KANEKO

引用次数: 0

Important Notice of the Cancellation of Special Section on Formal Approaches 关于取消正式申请特别部分的重要通知

4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-10-01 DOI: 10.1587/transinf.2022fop0000

引用次数: 0

Reconfigurable Pedestrian Detection System Using Deep Learning for Video Surveillance 基于深度学习的视频监控可重构行人检测系统

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2019edl8132

M. K. Jeevarajan, P. N. Kumar

引用次数: 0

Framework of Measuring Engagement with Access Logs Under Tracking Prevention for Affiliate Services 关联服务跟踪预防下访问日志参与度度量框架

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022ofp0001

Motoi Iwashita, Hirotaka Sugita

引用次数: 0

Discriminative Question Answering via Cascade Prompt Learning and Sentence Level Attention Mechanism 基于级联提示学习和句子级注意机制的辨别性问题回答

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022edp7225

Xiaoguang Yuan, Chaofan Dai, Zongkai Tian, Xinyu Fan, Yingyi Song, Ze Yu, Peifeng Wang, Wenjun Ke

引用次数: 0

Price Rank Prediction of a Company by Utilizing Data Mining Methods on Financial Disclosures 基于财务披露数据挖掘方法的公司价格排名预测

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022ofp0002

Mustafa Sami Kacar, Semih Yumusak, H. Kodaz

引用次数: 0

On Gradient Descent Training Under Data Augmentation with On-Line Noisy Copies 在线噪声副本数据增强下的梯度下降训练

4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2023edp7008

Katsuyuki HAGIWARA

{"title":"On Gradient Descent Training Under Data Augmentation with On-Line Noisy Copies","authors":"Katsuyuki HAGIWARA","doi":"10.1587/transinf.2023edp7008","DOIUrl":"https://doi.org/10.1587/transinf.2023edp7008","url":null,"abstract":"In machine learning, data augmentation (DA) is a technique for improving the generalization performance of models. In this paper, we mainly consider gradient descent of linear regression under DA using noisy copies of datasets, in which noise is injected into inputs. We analyze the situation where noisy copies are newly generated and injected into inputs at each epoch, i.e., the case of using on-line noisy copies. Therefore, this article can also be viewed as an analysis on a method using noise injection into a training process by DA. We considered the training process under three training situations which are the full-batch training under the sum of squared errors, and full-batch and mini-batch training under the mean squared error. We showed that, in all cases, training for DA with on-line copies is approximately equivalent to the ℓ2 regularization training for which variance of injected noise is important, whereas the number of copies is not. Moreover, we showed that DA with on-line copies apparently leads to an increase of learning rate in full-batch condition under the sum of squared errors and the mini-batch condition under the mean squared error. The apparent increase in learning rate and regularization effect can be attributed to the original input and additive noise in noisy copies, respectively. These results are confirmed in a numerical experiment in which we found that our result can be applied to usual off-line DA in an under-parameterization scenario and can not in an over-parametrization scenario. Moreover, we experimentally investigated the training process of neural networks under DA with off-line noisy copies and found that our analysis on linear regression can be qualitatively applied to neural networks.","PeriodicalId":55002,"journal":{"name":"IEICE Transactions on Information and Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136310000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IoT Modeling and Verification: From the CaIT Calculus to UPPAAL 物联网建模与验证:从CaIT演算到UPPAAL

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022edp7223

Ningning Chen, Huibiao Zhu

引用次数: 0

Protection Mechanism of Kernel Data Using Memory Protection Key 使用内存保护键的内核数据保护机制

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022icp0013

Hiroki Kuzuno, Toshihiro Yamauchi

引用次数: 0

A Large-Scale Investigation into the Possibility of Malware Infection of IoT Devices with Weak Credentials 对弱凭证物联网设备感染恶意软件可能性的大规模调查

IF 0.7 4区计算机科学

IEICE Transactions on Information and Systems Pub Date : 2023-09-01 DOI: 10.1587/transinf.2022ict0001

Kosuke Murakami, Takahiro Kasama, D. Inoue

引用次数: 1