IEEE Signal Processing Magazine最新文献_第6页

ILN Online Course ILN 在线课程

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3439908

引用次数: 0

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3439895

引用次数: 0

Deep Hypercomplex Networks for Spatiotemporal Data Processing: Parameter efficiency and superior performance [Hypercomplex Signal and Image Processing] 用于时空数据处理的深度超复杂网络：参数效率和卓越性能[超复杂信号和图像处理］

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3381808

Alabi Bojesomo;Panos Liatsis;Hasan Al Marzouqi

{"title":"Deep Hypercomplex Networks for Spatiotemporal Data Processing: Parameter efficiency and superior performance [Hypercomplex Signal and Image Processing]","authors":"Alabi Bojesomo;Panos Liatsis;Hasan Al Marzouqi","doi":"10.1109/MSP.2024.3381808","DOIUrl":"https://doi.org/10.1109/MSP.2024.3381808","url":null,"abstract":"Hypercomplex numbers, such as quaternions and octonions, have recently gained attention because of their advantageous properties over real numbers, e.g., in the development of parameter-efficient neural networks. For instance, the 16-component sedenion has the capacity to reduce the number of network parameters by a factor of 16. Moreover, hypercomplex neural networks offer advantages in the processing of spatiotemporal data as they are able to represent variable temporal data divisions through the hypercomplex components. Similarly, they support multimodal learning, with each component representing an individual modality. In this article, the key components of deep learning in the hypercomplex domain are introduced, encompassing concatenation, activation functions, convolution, and batch normalization. The use of the backpropagation algorithm for training hypercomplex networks is discussed in the context of hypercomplex algebra. These concepts are brought together in the design of a ResNet backbone using hypercomplex convolution, which is integrated within a U-Net configuration and applied in weather and traffic forecasting problems. The results demonstrate the superior performance of hypercomplex networks compared to their real-valued counterparts, given a fixed parameter budget, highlighting their potential in spatiotemporal data processing.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"101-112"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SPS Technical Committees SPS 技术委员会

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3439893

引用次数: 0

SPS Social Media SPS 社交媒体

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3437488

引用次数: 0

Demystifying the Hypercomplex: Inductive biases in hypercomplex deep learning [Hypercomplex Signal and Image Processing] 解密超复杂：超复杂深度学习中的归纳偏差 [超复杂信号与图像处理］

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3401622

Danilo Comminiello;Eleonora Grassucci;Danilo P. Mandic;Aurelio Uncini

{"title":"Demystifying the Hypercomplex: Inductive biases in hypercomplex deep learning [Hypercomplex Signal and Image Processing]","authors":"Danilo Comminiello;Eleonora Grassucci;Danilo P. Mandic;Aurelio Uncini","doi":"10.1109/MSP.2024.3401622","DOIUrl":"https://doi.org/10.1109/MSP.2024.3401622","url":null,"abstract":"Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimensional signals in real-world 3D and 4D paradigms. This article provides a foundational framework that serves as a road map for understanding why hypercomplex deep learning methods are so successful and how their potential can be exploited. Such a theoretical framework is described in terms of inductive bias, i.e., a collection of assumptions, properties, and constraints that are built into training algorithms to guide their learning process toward more efficient and accurate solutions. We show that it is possible to derive specific inductive biases in the hypercomplex domains, which extend complex numbers to encompass diverse numbers and data structures. These biases prove effective in managing the distinctive properties of these domains as well as the complex structures of multidimensional and multimodal signals. This novel perspective for hypercomplex deep learning promises to both demystify this class of methods and clarify their potential, under a unifying framework, and in this way, promotes hypercomplex models as viable alternatives to traditional real-valued deep learning for multidimensional signal processing.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"59-71"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Special Issue: Artificial Intelligence for Education: A Signal Processing Perspective 特刊：人工智能教育：信号处理视角

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3439148

引用次数: 0

Call for Papers: Special Issue on The Mathematics of Deep Learning 征稿：深度学习数学特刊

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3439150

引用次数: 0

New Society Officer Elected [Society News] 新当选的学会官员 [学会新闻］

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3415288

引用次数: 0

Quaternion Neural Networks: A physics-incorporated intelligence framework [Hypercomplex Signal and Image Processing] 四元神经网络：融入物理学的智能框架[超复杂信号与图像处理］

IF 9.4 1区工程技术

IEEE Signal Processing Magazine Pub Date : 2024-08-20 DOI: 10.1109/MSP.2024.3384179

Akira Hirose;Fang Shang;Yuta Otsuka;Ryo Natsuaki;Yuya Matsumoto;Naoto Usami;Yicheng Song;Haotian Chen

引用次数: 0