Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3381808
Alabi Bojesomo;Panos Liatsis;Hasan Al Marzouqi
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.
{"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}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3437488
{"title":"SPS Social Media","authors":"","doi":"10.1109/MSP.2024.3437488","DOIUrl":"https://doi.org/10.1109/MSP.2024.3437488","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"5-5"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640318","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3401622
Danilo Comminiello;Eleonora Grassucci;Danilo P. Mandic;Aurelio Uncini
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.
{"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}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3439148
{"title":"Special Issue: Artificial Intelligence for Education: A Signal Processing Perspective","authors":"","doi":"10.1109/MSP.2024.3439148","DOIUrl":"https://doi.org/10.1109/MSP.2024.3439148","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"15-15"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640327","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3439150
{"title":"Call for Papers: Special Issue on The Mathematics of Deep Learning","authors":"","doi":"10.1109/MSP.2024.3439150","DOIUrl":"https://doi.org/10.1109/MSP.2024.3439150","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"17-17"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640315","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-20DOI: 10.1109/MSP.2024.3415288
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
提供从业人员和研究人员感兴趣的社会信息，包括新闻、评论或技术说明。
{"title":"New Society Officer Elected [Society News]","authors":"","doi":"10.1109/MSP.2024.3415288","DOIUrl":"https://doi.org/10.1109/MSP.2024.3415288","url":null,"abstract":"Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"114-114"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10640319","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Why quaternions in neural networks (NNs)? Are there quaternions in the human brain? “No” may be an ordinary answer. However, quaternion NNs (QNNs) are a powerful framework that strongly connects artificial intelligence (AI) and the real world. In this article, we deal with NNs based on quaternions and describe their basics and features. We also detail the underlying ideas in their engineering applications, especially when we adaptively process the polarization information of electromagnetic waves. We focus on their role in remote sensing, such as Earth observation radar mounted on artificial satellites or aircraft and underground radar, as well as mobile communication. There, QNNs are a class of NNs that know physics, especially polarization, composing a framework by fusing measurement physics with adaptive-processing mathematics. This fusion realizes a seamless integration of measurement and intelligence, contributing to the construction of a human society having harmony between AI and real human lives.
{"title":"Quaternion Neural Networks: A physics-incorporated intelligence framework [Hypercomplex Signal and Image Processing]","authors":"Akira Hirose;Fang Shang;Yuta Otsuka;Ryo Natsuaki;Yuya Matsumoto;Naoto Usami;Yicheng Song;Haotian Chen","doi":"10.1109/MSP.2024.3384179","DOIUrl":"https://doi.org/10.1109/MSP.2024.3384179","url":null,"abstract":"Why quaternions in neural networks (NNs)? Are there quaternions in the human brain? “No” may be an ordinary answer. However, quaternion NNs (QNNs) are a powerful framework that strongly connects artificial intelligence (AI) and the real world. In this article, we deal with NNs based on quaternions and describe their basics and features. We also detail the underlying ideas in their engineering applications, especially when we adaptively process the polarization information of electromagnetic waves. We focus on their role in remote sensing, such as Earth observation radar mounted on artificial satellites or aircraft and underground radar, as well as mobile communication. There, QNNs are a class of NNs that know physics, especially polarization, composing a framework by fusing measurement physics with adaptive-processing mathematics. This fusion realizes a seamless integration of measurement and intelligence, contributing to the construction of a human society having harmony between AI and real human lives.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 3","pages":"88-100"},"PeriodicalIF":9.4,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142013277","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}
Pub Date : 2024-03-01DOI: 10.1109/MSP.2024.3404210
Tülay Adali
For reasons beyond our control, the issues of IEEE Signal Processing Magazine arrive to you with delays this year. As you receive the current March issue, we are back from another edition of our flagship conference, the IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), which took place in Seoul, Korea, 14–19 April 2024. It was successful and vibrant, and, with 4,432 attendees and 2,826 accepted papers (out of 5,896 submitted), it was bigger than ever. At the risk of being labeled a grumpy Muppet, I will note that ICASSPs are now a tad too big for me, as I often found myself at a loss trying to choose among a seemingly endless number of attractive sessions and events at any given time. Of course, we still have our workshops, which are intimate and focused, and a number of them are even single tracks.
{"title":"Today’s Rapidly Evolving Education Landscape: Challenges and Opportunities [From the Editor]","authors":"Tülay Adali","doi":"10.1109/MSP.2024.3404210","DOIUrl":"https://doi.org/10.1109/MSP.2024.3404210","url":null,"abstract":"For reasons beyond our control, the issues of \u0000<italic>IEEE Signal Processing Magazine</i>\u0000 arrive to you with delays this year. As you receive the current March issue, we are back from another edition of our flagship conference, the IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP), which took place in Seoul, Korea, 14–19 April 2024. It was successful and vibrant, and, with 4,432 attendees and 2,826 accepted papers (out of 5,896 submitted), it was bigger than ever. At the risk of being labeled a grumpy Muppet, I will note that ICASSPs are now a tad too big for me, as I often found myself at a loss trying to choose among a seemingly endless number of attractive sessions and events at any given time. Of course, we still have our workshops, which are intimate and focused, and a number of them are even single tracks.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 2","pages":"3-5"},"PeriodicalIF":14.9,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10558746","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1109/MSP.2024.3365463
Alfredo Alcayde;Jorge Ventura;Francisco G. Montoya
This article aims to identify core research directions and provide a comprehensive overview of major advancements in the field of hypercomplex signal and image processing techniques using network graph theory. The methodology employs community detection algorithms on research networks to uncover relationships among researchers and topic fields in the hypercomplex domain. This is accomplished through a comprehensive academic database search and metadata analysis from pertinent papers. The article focuses on the utility of these techniques in various applications and the value of mathematically rich frameworks. The results demonstrate how optimized network-based approaches can determine common topics and emerging lines of research. The article identifies distinct core research directions, including significant advancements in image/video processing, computer vision, signal processing, security, navigation, and machine learning within the hypercomplex domain. Current trends, challenges, opportunities, and the most promising directions in hypercomplex signal and image processing are highlighted based on a thorough literature analysis. This provides actionable insights for researchers to advance this domain.
{"title":"Hypercomplex Techniques in Signal and Image Processing Using Network Graph Theory: Identifying core research directions [Hypercomplex Signal and Image Processing]","authors":"Alfredo Alcayde;Jorge Ventura;Francisco G. Montoya","doi":"10.1109/MSP.2024.3365463","DOIUrl":"https://doi.org/10.1109/MSP.2024.3365463","url":null,"abstract":"This article aims to identify core research directions and provide a comprehensive overview of major advancements in the field of hypercomplex signal and image processing techniques using network graph theory. The methodology employs community detection algorithms on research networks to uncover relationships among researchers and topic fields in the hypercomplex domain. This is accomplished through a comprehensive academic database search and metadata analysis from pertinent papers. The article focuses on the utility of these techniques in various applications and the value of mathematically rich frameworks. The results demonstrate how optimized network-based approaches can determine common topics and emerging lines of research. The article identifies distinct core research directions, including significant advancements in image/video processing, computer vision, signal processing, security, navigation, and machine learning within the hypercomplex domain. Current trends, challenges, opportunities, and the most promising directions in hypercomplex signal and image processing are highlighted based on a thorough literature analysis. This provides actionable insights for researchers to advance this domain.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 2","pages":"14-28"},"PeriodicalIF":14.9,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326385","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：