Uncini | Mathematical Elements of Modern Artificial Intelligence | Buch | 978-3-032-48241-9 | www.sack.de

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

Reihe: Studies in Computational Intelligence

Uncini

Mathematical Elements of Modern Artificial Intelligence

Volume II: Statistical Foundations, Representation Learning, and Generative Modeling
Erscheinungsjahr 2027
ISBN: 978-3-032-48241-9
Verlag: Springer

Volume II: Statistical Foundations, Representation Learning, and Generative Modeling

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

Reihe: Studies in Computational Intelligence

ISBN: 978-3-032-48241-9
Verlag: Springer


The book develops the probabilistic, statistical, informational, and representational structures underlying modern artificial intelligence. It brings together random variables and distributions, estimation theory, stochastic processes, Markov models, graphical representations, information measures, and dimensionality reduction within a unified mathematical framework. These foundations lead to modern representation learning, including autoencoders, contrastive and self-supervised methods, attention, Transformers, and neural state-space models. The book then examines approximate inference and generative modeling through Monte Carlo methods, variational inference, variational autoencoders, adversarial learning, stochastic sampling, and diffusion- and score-based models. Its final chapter connects these principles to foundation models and interactive AI systems, addressing reasoning, planning, external tools, retrieval, memory, reinforcement learning, and multi-agent coordination. The exposition combines mathematical rigor with progressive explanations, examples, exercises, and advanced projects. Together with Volume I, which covers mathematical foundations, optimization, and learning algorithms, it provides a complementary view of modern AI; however, the volumes are designed to be self-contained and may be read independently. The book is intended for graduate students, researchers, and practitioners in machine learning, signal processing, applied mathematics, and related fields.

Uncini Mathematical Elements of Modern Artificial Intelligence jetzt bestellen!

Zielgruppe


Upper undergraduate


Autoren/Hrsg.


Weitere Infos & Material


Random Variables and Probabilistic Models.- Estimation Theory for Machine Learning.- Stochastic Nonlinear Dynamics.- Graphical and Graph-Based Models for Machine Learning.- Information Theory for Machine Learning.- Dimensionality Reduction and Representation Learning.- Approximate Inference for Generative Modeling.- Reasoning, Planning, Memory, and Learning in Interactive AI Systems.- Index.


Aurelio Uncini is professor at the Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Italy, where he founded and leads the Intelligent Signal Processing and Multimedia (ISPAMM) Laboratory. His research spans adaptive signal processing, neural networks, deep learning, nonlinear and hypercomplex models, audio and speech processing, representation learning, and generative artificial intelligence. He is (co-)author of more than 320 scientific publications and two books: Digital Audio Processing Fundamentals (Springer, 2023) and Fundamentals of Adaptive Signal Processing (Springer, 2015). His recent research interests focus on hypercomplex deep learning, quaternion and wavelet neural architectures, multimodal learning, diffusion-based generative models, and AI-driven signal processing for audio, images, medical imaging, and 3D audio. He has served as Program Chair of IJCNN 2025, General Chair of IEEE MLSP 2023, and Program Chair of IEEE MLSP 2016.



Ihre Fragen, Wünsche oder Anmerkungen
Vorname*
Nachname*
Ihre E-Mail-Adresse*
Kundennr.
Ihre Nachricht*
Lediglich mit * gekennzeichnete Felder sind Pflichtfelder.
Wenn Sie die im Kontaktformular eingegebenen Daten durch Klick auf den nachfolgenden Button übersenden, erklären Sie sich damit einverstanden, dass wir Ihr Angaben für die Beantwortung Ihrer Anfrage verwenden. Selbstverständlich werden Ihre Daten vertraulich behandelt und nicht an Dritte weitergegeben. Sie können der Verwendung Ihrer Daten jederzeit widersprechen. Das Datenhandling bei Sack Fachmedien erklären wir Ihnen in unserer Datenschutzerklärung.