Pub Date : 2024-10-11DOI: 10.1109/MSP.2024.3464888
{"title":"Join the SPS","authors":"","doi":"10.1109/MSP.2024.3464888","DOIUrl":"https://doi.org/10.1109/MSP.2024.3464888","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"C3-C3"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714504","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142409049","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 : 2024-10-11DOI: 10.1109/MSP.2024.3385950
Tom Tirer;Raja Giryes;Se Young Chun;Yonina C. Eldar
Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases, there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data are scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited. Using this information is the key to deep internal learning strategies, which may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey article aims at covering deep internal learning techniques that have been proposed in the past few years for these two important directions. While our main focus is on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities.
{"title":"Deep Internal Learning: Deep learning from a single input","authors":"Tom Tirer;Raja Giryes;Se Young Chun;Yonina C. Eldar","doi":"10.1109/MSP.2024.3385950","DOIUrl":"https://doi.org/10.1109/MSP.2024.3385950","url":null,"abstract":"Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases, there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data are scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited. Using this information is the key to deep internal learning strategies, which may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey article aims at covering deep internal learning techniques that have been proposed in the past few years for these two important directions. While our main focus is on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"40-57"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408920","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 : 2024-10-11DOI: 10.1109/MSP.2024.3431168
Virginia Bordignon;Vincenzo Matta;Ali H. Sayed
By “social learning,” in this article we refer to mechanisms for opinion formation and decision making over graphs and the study of how agents’ decisions evolve dynamically through interactions with neighbors and the environment. The study of social learning strategies is critical for at least two reasons. On one hand, it allows for a deeper understanding of the fundamental cognitive mechanisms that enable opinion formation over networks and the propagation of information or misinformation over them. On the other hand, these same learning strategies are effective for decision making by networked agents under challenging conditions, such as highly dynamic environments, nonstationary models and data, untruthful or malicious agents, sparsely connected graphs, and constrained communication. The article presents a unifying framework that covers several cases of interest, such as single-agent Bayesian learning, multiagent non-Bayesian learning, adaptive social learning, social machine learning, partial information sharing, influence discovery, and many others. The presentation highlights important limitations of the traditional social learning strategies. One limitation is the inability to track well drifting conditions. Traditional approaches lead to stubborn agents, which resist new states of information and are slow to react to changes in the environment, like an opinion that changes over time. Another limitation of the traditional strategies is that they assume perfect knowledge of the data models, which is seldom available in practice. The article illustrates recent advances that address these issues. We show how to endow multiagent networks with adaptation abilities and how to build social machine learning solutions that learn the necessary models directly from the data. These are fundamental steps toward the construction of socially intelligent networks, capable of exploiting cooperation and diversity across the agents to guarantee reliable learning performance under nonstationary, heterogeneous, and uncertain environments.
{"title":"Socially Intelligent Networks: A framework for decision making over graphs","authors":"Virginia Bordignon;Vincenzo Matta;Ali H. Sayed","doi":"10.1109/MSP.2024.3431168","DOIUrl":"https://doi.org/10.1109/MSP.2024.3431168","url":null,"abstract":"By “social learning,” in this article we refer to mechanisms for opinion formation and decision making over graphs and the study of how agents’ decisions evolve dynamically through interactions with neighbors and the environment. The study of social learning strategies is critical for at least two reasons. On one hand, it allows for a deeper understanding of the fundamental cognitive mechanisms that enable opinion formation over networks and the propagation of information or misinformation over them. On the other hand, these same learning strategies are effective for decision making by networked agents under challenging conditions, such as highly dynamic environments, nonstationary models and data, untruthful or malicious agents, sparsely connected graphs, and constrained communication. The article presents a unifying framework that covers several cases of interest, such as single-agent Bayesian learning, multiagent non-Bayesian learning, adaptive social learning, social machine learning, partial information sharing, influence discovery, and many others. The presentation highlights important limitations of the traditional social learning strategies. One limitation is the inability to track well drifting conditions. Traditional approaches lead to stubborn agents, which resist new states of information and are slow to react to changes in the environment, like an opinion that changes over time. Another limitation of the traditional strategies is that they assume perfect knowledge of the data models, which is seldom available in practice. The article illustrates recent advances that address these issues. We show how to endow multiagent networks with adaptation abilities and how to build social machine learning solutions that learn the necessary models directly from the data. These are fundamental steps toward the construction of socially intelligent networks, capable of exploiting cooperation and diversity across the agents to guarantee reliable learning performance under nonstationary, heterogeneous, and uncertain environments.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"20-39"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408900","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 : 2024-10-11DOI: 10.1109/MSP.2024.3405110
Liming Xiu
The history of electronics is studied from physical and evolutionary viewpoints, identifying a crisis of “space overexploitation.” This space-central practice is signified by Moore’s Law, the 1.0 version. Electronics is also examined in philosophical standing, leading to an awareness that a paradigm was formed around the late 1940s. It is recognized that this paradigm is of reductionist nature and consciousness is not ready to emerge therein. A new paradigm is suggested that diverts from the space-central practice to the foresight of putting space and time on equal footing. By better utilizing time, it offers a detour from the space crisis. Moreover, the paradigm is prepared for holism by balancing the roles of space and time. Integrating the entwined narratives of physical, evolutionary, and philosophical, an argument is made that, after decades of adventure, electronics is due for an overhaul. The two foundational pillars, space and time, ought to be used more meticulously to rectify the electronics edifice. This perspective of shifting from space-central to balanced space-time is proposed as Moore’s Law 2.0 and is embodied as second paradigm, a holistic one. The aim is to transcend reductionism to holism, paving the way for the likely emergence of consciousness.
{"title":"From Space-Central to Space-Time Balanced: A Perspective for Moore’s Law 2.0 and a Holistic Paradigm for Emergence [Perspectives]","authors":"Liming Xiu","doi":"10.1109/MSP.2024.3405110","DOIUrl":"https://doi.org/10.1109/MSP.2024.3405110","url":null,"abstract":"The history of electronics is studied from physical and evolutionary viewpoints, identifying a crisis of “space overexploitation.” This space-central practice is signified by Moore’s Law, the 1.0 version. Electronics is also examined in philosophical standing, leading to an awareness that a paradigm was formed around the late 1940s. It is recognized that this paradigm is of reductionist nature and consciousness is not ready to emerge therein. A new paradigm is suggested that diverts from the space-central practice to the foresight of putting space and time on equal footing. By better utilizing time, it offers a detour from the space crisis. Moreover, the paradigm is prepared for holism by balancing the roles of space and time. Integrating the entwined narratives of physical, evolutionary, and philosophical, an argument is made that, after decades of adventure, electronics is due for an overhaul. The two foundational pillars, space and time, ought to be used more meticulously to rectify the electronics edifice. This perspective of shifting from space-central to balanced space-time is proposed as Moore’s Law 2.0 and is embodied as second paradigm, a holistic one. The aim is to transcend reductionism to holism, paving the way for the likely emergence of consciousness.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"10-18"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142409071","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 : 2024-10-11DOI: 10.1109/MSP.2024.3436488
José Antonio Apolinário
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":"Fast Fourier Transform-Based Computation of Uniform Linear Array Beam Patterns [Tips & Tricks]","authors":"José Antonio Apolinário","doi":"10.1109/MSP.2024.3436488","DOIUrl":"https://doi.org/10.1109/MSP.2024.3436488","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 4","pages":"90-95"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714911","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408898","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 : 2024-10-11DOI: 10.1109/MSP.2024.3442648
Aggelos Bletsas
Recounts the career and contributions of Prof. Sophocles J. Orfanidis.
介绍索福克勒斯-J-奥尔法尼蒂斯教授的职业生涯和贡献。
{"title":"Honoring Prof. Sophocles J. Orfanidis [In Memoriam]","authors":"Aggelos Bletsas","doi":"10.1109/MSP.2024.3442648","DOIUrl":"https://doi.org/10.1109/MSP.2024.3442648","url":null,"abstract":"Recounts the career and contributions of Prof. Sophocles J. Orfanidis.","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"106-106"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714908","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408926","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 : 2024-10-11DOI: 10.1109/MSP.2024.3465068
Tülay Adali
{"title":"Interdisciplinarity: The Clear Path Forward [From the Editor]","authors":"Tülay Adali","doi":"10.1109/MSP.2024.3465068","DOIUrl":"https://doi.org/10.1109/MSP.2024.3465068","url":null,"abstract":"","PeriodicalId":13246,"journal":{"name":"IEEE Signal Processing Magazine","volume":"41 4","pages":"3-4"},"PeriodicalIF":9.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714904","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408929","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}
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：