Model-Based Deep Learning

DOI10.1561/2000000113zbMATH Open1525.68137arXiv2306.04469OpenAlexW4386037851MaRDI QIDQ6139543FDOQ6139543

Nir Shlezinger, Y. C. Eldar

Publication date: 19 December 2023

Published in: Foundations and Trends® in Signal Processing (Search for Journal in Brave)

Abstract: Signal processing traditionally relies on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and additional domain knowledge. Simple classical models are useful but sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior. More recently, deep learning approaches that use deep neural networks are becoming increasingly popular. Deep learning systems do not rely on mathematical modeling, and learn their mapping from data, which allows them to operate in complex environments. However, they lack the interpretability and reliability of model-based methods, typically require large training sets to obtain good performance, and tend to be computationally complex. Model-based signal processing methods and data-centric deep learning each have their pros and cons. These paradigms can be characterized as edges of a continuous spectrum varying in specificity and parameterization. The methodologies that lie in the middle ground of this spectrum, thus integrating model-based signal processing with deep learning, are referred to as model-based deep learning, and are the focus here. This monograph provides a tutorial style presentation of model-based deep learning methodologies. These are families of algorithms that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches. Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data. We accompany our presentation with running examples, in super-resolution, dynamic systems, and array processing. We show how they are expressed using the provided characterization and specialized in each of the detailed methodologies.

Full work available at URL: https://arxiv.org/abs/2306.04469

zbMATH Keywords

classificationdeep learningregressionestimationmodel choicestatistical signal processinginverse problemsdetectiondecodingstatistical machine learning

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to computer science (68-02) Artificial neural networks and deep learning (68T07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning Deep Architectures for AI
• Understanding Machine Learning
• The Design of Approximation Algorithms
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Model-Driven Deep Learning for MIMO Detection
• Learning to Detect

Cited In (3)

• Applying MDL to learn best model granularity
• Deep multiscale model learning
• Learning from small data sets: patch-based regularizers in inverse problems for image reconstruction

This page was built for publication: Model-Based Deep Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6139543)