Neural Networks

A Concise Theoretical Foundation
Erscheinungsjahr 2027
ISBN: 978-0-443-51339-8
Verlag: Elsevier Science

Buch, Englisch, 300 Seiten, Format (B × H): 191 mm x 235 mm

This book presents deep learning as both a mathematical discipline and an applied field,

connecting theoretical principles with the modeling and design choices that shape modern

neural systems. It explores how neural networks are formulated and how they learn, from

multilayer perceptrons, activation and loss functions, optimization, and backpropagation

to questions of expressivity and generalization. These ideas are applied to neural

architectures for different forms of data, including convolutional, recurrent, and graph

neural networks, with attention to the mathematical principles, training challenges, and

design choices that distinguish them. The book then turns to generative models and

sequential decision-making, covering variational and adversarial models, diffusion, and

reinforcement learning.
The later parts follow the evolution of neural networks toward increasingly general systems,

exploring attention and transformer architectures, multimodal models, large language

models, retrieval-augmented systems, and autonomous agents. The book also considers

directions beyond conventional deep learning, including continuous-time and physics-informed neural networks, biologically-inspired and neuromorphic models, Bayesian

approaches to uncertainty, and quantum neural networks.
The term “theoretical” in the title, Neural Networks: A Concise Theoretical Foundation, refers to the mathematical formulation of neural networks, not to a comprehensive, proof-oriented treatment of neural network theory. Organized in four parts, the book connects mathematical descriptions with

the architectures, learning methods, and emerging directions that continue to shape neural computation.

Autoren/Hrsg.

Sarraf, Aydin

Kucerovsky, Daniel Z.

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Natürliche Sprachen & Maschinelle Übersetzung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Fuzzy-Systeme

Inhaltsverzeichnis

NotationsPart I: Foundations of Neural Networks1. Introduction
2. Multilayer Perceptrons
3. Training of Neural Networks
4. Expressivity and GeneralizationPart II: Neural Architectures for Diverse Data Modalities5. Convolutional Neural Networks
6. Recurrent Neural Networks
7. Graph Neural NetworksPart III: The Rise of General Intelligence8. Generative Neural Networks
9. Deep Reinforcement Learning
10. Attention-Based Neural Networks
11. Large Language Models and AgentsPart IV: New Computing Frontiers12. Continuous-Time Neural Networks
13. Biologically-Inspired Neural Networks
14. Bayesian Neural Networks
15. Quantum Neural Networks

Über Autor(innen)

Kucerovsky, Daniel Z.
Dan Kucerovsky studied at Magdalen College, University of Oxford and is now a
mathematician and researcher at the University of New Brunswick, specializing in abstract algebra, automorphisms, computational group theory, cryptography, functional analysis,
and summability. His work connects rigorous theory with algorithms and applications, from
finite-group structure to discrete logarithms. Dan explores the evolving relationship
between artificial intelligence, mathematical reasoning, and research.

Sarraf, Aydin
Aydin Sarraf is a data scientist, and artificial intelligence professional with more than ten
years of experience in the field. His work spans artificial intelligence, machine learning,
neural networks, and the mathematical principles underlying intelligent systems. Over the course of his career, he has contributed to published research papers and patents in
artificial intelligence, machine learning, and related areas. Aydin combines theoretical
knowledge with practical experience, with a particular interest in making complex AI
concepts accessible without compromising technical rigor.