{"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}
{"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}
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}
{"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}
{"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}
{"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}
{"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}