The guide methodically unpacks the building blocks of machine learning, covering supervised, unsupervised, and reinforcement learning in clear, understandable language. Each type is illustrated with relatable scenarios, such as spam detection and anomaly discovery, while illuminating core ideas like training, features, and dealing with common challenges such as bias or overfitting. Further, it introduces neural networks and deep learning, explaining both the transformative impact and the limitations of these technologies, as well as practical techniques for preparing data, evaluating models, and ensuring trustworthiness through explainable AI.
Concluding with a thoughtful exploration of ethics, societal impact, and the future of AI, the book emphasizes responsible innovation and the enduring role of human judgment. It examines not only the opportunities brought by AI but also the critical questions around fairness, privacy, and accountability. Balancing technical clarity with big-picture insights, "How Machines Learn" is an ideal starting point for students, professionals, and enthusiasts eager to understand and thoughtfully navigate our increasingly AI-driven world.
Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, CY, CZ, D, DK, EW, E, FIN, F, GR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.