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

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

The flexibility and dexterity of human limbs rely on the processing of a vast quantity of signals within the sensory-motor networks in the brain and spinal cord, distilled into stimuli that govern the commands and movements. Hence, the use of assistive devices, such as robotic limbs or exoskeletons, is critically dependent on the processing of a large number of heterogeneous signals to mimic natural

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

We show how to design a cheap system for detecting when music is present in audio recordings. We make use of a small neural network consisting of a simple multilayer perceptron (MLP) along with compact features derived from the mel spectrogram by means of temporal integration.

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

Recounts the career and contributions of Prof. Sophocles J. Orfanidis.

In the first issue of 2024, we introduced the new lead editorial team of IEEE Signal Processing Magazine ( SPM ), composed of our four area editors. Their terms started with mine this January, and they oversee the Society e-newsletter and the three main components of our magazine: feature articles, special issues, and columns and forum articles. As a team, we have undertaken a complete revision of

When we set out to host ICASSP 2024, in Seoul, South Korea, we had three goals in mind: organize an outstanding technical program, provide an excellent and engaging venue to foster meetings to exchange ideas, and deliver the most welcoming experience to our attendees. With the hard work and commitment from the outstanding organizing committee (OC), we were able to achieve these goals. The culturally

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

The digital twin of the ocean (DTO) is a groundbreaking concept that uses interactive simulations to improve decision-making and promote sustainability in earth science. The DTO effectively combines ocean observations, artificial intelligence (AI), advanced modeling, and high-performance computing to unite digital replicas, forecasting, and what-if scenario simulations of the ocean systems. However

Learning machines for vector sensor data are naturally developed in the quaternion domain and are underpinned by quaternion statistics. To this end, we revisit the “augmented” representation basis for discrete quaternion random variables (RVs) ${\bf{q}}^{a}[n]$ , i.e., ${[}{\bf{q}}{[}{n}{]}\;{\bf{q}}^{\imath}{[}{n}{]}\;{\bf{q}}^{\jmath}{[}{n}{]}{\bf{q}}^{\kappa}{[}{n}{]]}$ , and demonstrate its pivotal

Hypercomplex signal and image processing extends upon conventional methods by using hypercomplex numbers in a unified framework for algebra and geometry. The special issue is divided into two parts and is focused on current advances and applications in computational signal and image processing in the hypercomplex domain. The first part offered well-rounded coverage of the field, with seven articles

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

Hypercomplex signal processing (HSP) provides state-of-the-art tools to handle multidimensional signals by harnessing the intrinsic correlation of the signal dimensions through Clifford algebra. Recently, the hypercomplex representation of the phase retrieval (PR) problem, wherein a complex-valued signal is estimated through its intensity-only projections, has attracted significant interest. The hypercomplex

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

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

Despite the many successful applications of deep learning models for multidimensional signal and image processing, most traditional neural networks process data represented by (multidimensional) arrays of real numbers. The intercorrelation between feature channels is usually expected to be learned from the training data, requiring numerous parameters and careful training. In contrast, vector-valued