Continual Learning Through the Lens of Adaptive Filtering: A mathematical tutorial
Abstract: Continual learning refers to the problem of learning multiple tasks presented sequentially to the learner without forgetting previously…
Read moreSPM Articles
Rapture of the Deep: Highs and lows of sparsity in a world of depths
Abstract: Promoting sparsity in deep networks is a natural way to control their complexity, and it is a timely endeavor since practical neural model…
Read moreDeploying AI for Signal Processing Education: Selected Challenges and Intriguing Opportunities
Abstract: Powerful artificial intelligence (AI) tools that have emerged in recent years—including large language models (LLMs), automated coding…
Read morePerspectives: Transcending Reductionism and Dualism: Philosophical Critique of Electronics and a Vision for Brain-Mimicking Artificial Intelligence Under Moore’s Law 2.0
Abstract: This article argues that the quest for brain-mimicking artificial intelligence is no longer limited by algorithms or transistor counts, but…
Read moreQuadratic Transform for Fractional Programming in Signal Processing and Machine Learning: A unified approach for solving optimization problems involving ratios
Fractional programming (FP) is a branch of mathematical optimization that deals with the optimization of ratios. It is an invaluable tool for signal…
Read moreConversational Agents in the Era of Large Language Models
With the advent of large language models (LLMs), the concept of artificial intelligence (AI) agents capable of decision making and action execution…
Read moreICASSP@50: A Recap [Conference Highlights]
The Golden Jubilee edition of the IEEE Signal Processing Society’s (SPS’s) flagship conference, IEEE International Conference on Acoustics, Speech…
Read moreWaveforms for Computing Over the Air: A groundbreaking approach that redefines data aggregation
Over-the-air computation (AirComp) leverages the signal superposition characteristic of wireless multiple-access channels (MACs) to perform mathematical computations. Initially introduced to enhance communication reliability in interference channels and wireless sensor networks (WSNs), AirComp has more recently found applications in task-oriented communications like wireless distributed learning and in wireless control systems.
Ode to Masterfully Written Textbooks: And remembering Simon Haykin [From the Editor]
The tutorial “Introducing Information Metrics for Statistical Signal Processing,” [A1] provided the inspiration for our cover in this issue…
Read moreRaison d’Être: 2025 Edition [President’s Message]
In his January 2012 column for IEEE Signal Processing Magazine, K. J. Ray Liu, then president of the IEEE Signal Processing Society (SPS), highlighted the importance of establishing a formal community when individuals come together to create a professional society [1]. He emphasized that the Society’s primary mission, its raison d’être, is to serve its community, and the key to achieving this mission is to serve its members effectively.
