Quantum Machine Learning Codebook

Build Hybrid Models with PennyLane, Cirq, and Qiskit in Notebooks
Erscheinungsjahr 2026
ISBN: 978-3-032-33784-9
Verlag: Springer

Buch, Englisch, 113 Seiten, Format (B × H): 155 mm x 235 mm

Reihe: SpringerBriefs in Computer Science

This book covers an end-to-end, build-first path into practical quantum machine learning. It begins with foundational concepts explained in plain language, then moves through trainable variational classifiers, quantum kernel methods, and Born-style generative models. It continues with hybrid deep-learning workflows and simulator-to-hardware transition practices, and concludes with a full capstone and reproducibility playbook. Every chapter is tied to runnable notebooks so readers can execute, modify, and verify each method directly.
The text is designed for readers who want working systems, not theory alone. It shows how to structure experiments, control variance, compare against strong classical baselines, and report results with technical honesty. Special focus is given to shot management, cross-framework parity, transpilation effects, and cost-aware evaluation so that claims remain methodologically defensible.
Across the chapters, the same modeling ideas are translated across PennyLane, Cirq, and Qiskit to promote portability beyond any single stack. The result is a practical reference for learners and practitioners who need to design, train, evaluate, and communicate hybrid quantum-classical models under real engineering constraints.

Zielgruppe

Professional/practitioner

Autoren/Hrsg.

Wayo, Dennis

Groppe, Sven

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Informatik Mathematik für Informatiker
• Naturwissenschaften Physik Quantenphysik

Inhaltsverzeichnis

.- Start Here: QML in Plain Language.
.- First Trainable Model: Variational Classifiers.
.- Beyond Classifiers: Kernels and Generative Models.
.- Hybrid Deep Learning Workflows.
.- From Simulator to Hardware.
.- Capstone and Reproducibility Playbook.

Über Autor(innen)

Dennis Wayo is a quantum software researcher and scientific software engineer focused on fault-tolerant quantum computing, photonic simulation, and reproducible computational pipelines. He is the creator of LiDMaS+, a replay-driven logical-decoder benchmarking platform, and SchroSIM, a hardware-agnostic photonic quantum simulator. His work spans decoder benchmarking, continuous-variable and hybrid quantum architectures, and architecture-level performance analysis across Python, Rust, C++, and Swift. He holds a PhD in Chemical Engineering and is currently pursuing a PhD in Computer Science at TU Bergakademie Freiberg (TUBAF) and an M.S. in Computer Science at the Georgia Institute of Technology (Georgia Tech), with interests in quantum architecture, compiler-aware simulation, and scalable scientific software for quantum error correction.

Prof. Dr. habil. Sven Groppe is a computer scientist and the holder of the Professorship of Artificial Intelligence at TU Bergakademie Freiberg (Institute of Computer Science, Faculty of Mathematics and Computer Science). His research spans quantum computing software and frameworks, high-level quantum programming and optimization, artificial intelligence, data management, semantic technologies, and large-scale distributed systems. He has led and coordinated multiple funded research projects and contributes to interdisciplinary work at the intersection of quantum computing, intelligent systems, and data-intensive computing.