1st Edition

Mathematical Foundations for Deep Learning

By Mehdi Ghayoumi Copyright 2026
386 Pages 108 Color Illustrations
by Chapman & Hall

386 Pages 108 Color Illustrations
by Chapman & Hall

Mathematical Foundations for Deep Learning bridges the gap between theoretical mathematics and practical applications in artificial intelligence (AI). This guide delves into the fundamental mathematical concepts that power modern deep learning, equipping readers with the tools and knowledge needed to excel in the rapidly evolving field of artificial intelligence. Designed for learners at all... Read more

Preface   About the author   Acknowledgements   1. Introduction   2. Linear Algebra   3. Multivariate Calculus   4. Probability Theory and Statistics   5. Optimization Theory   6. Information Theory   7. Graph Theory   8. Differential Geometry   9. Topology in Deep Learning   10. Harmonic Analysis for CNNs   11. Dynamical Systems and Differential Equations for RNNs   12. Quantum Computing

Biography

Dr. Mehdi Ghayoumi is an Assistant Professor at the Center for Criminal Justice, Intelligence, and Cybersecurity at SUNY Canton, recognized for his excellence in teaching and research—including previous roles at SUNY Binghamton and Kent State University, where he received consecutive Teaching Awards in 2016 and 2017. His multidisciplinary research focuses on machine learning, robotics, human-robot interaction, and privacy, aiming to develop practical systems for real-world applications in manufacturing, biometrics, and healthcare. Actively contributing to the academic community, Dr. Ghayoumi develops courses in emerging technologies and serves on technical program committees and editorial boards for leading conferences and journals in his field.