Passt nicht? Macht nichts! Sie können Artikel bis zu 30 Tage zurückgeben
Mit einem Geschenkgutschein können Sie nichts falsch machen. Der Beschenkte kann sich im Tausch gegen einen Geschenkgutschein etwas aus unserem Sortiment aussuchen.
Bis zu 30 Tage Rückgaberecht
Deep Learning from Curiosity to Mastery: Volume 1, Foundations of Neural Networks is an intuition-first introduction to deep learning designed for beginners, students, engineers, researchers, and practitioners. Rather than assuming a strong background in mathematics or programming, the book builds the foundations step by step, connecting intuition, mathematics, Python, PyTorch, model evaluation, and practical implementation.
Readers begin with the fundamental ideas behind artificial neurons and neural networks, then learn how networks actually learn through forward propagation, loss functions, gradients, backpropagation, and optimization. Mathematical concepts are introduced in context through focused Math Boxes, allowing readers to understand not only how neural networks work, but why.
The book also includes practical introductions to Python and PyTorch, making it accessible to readers who are new to either. Hands-on examples, runnable Google Colab notebooks, exercises, assessments, and end-to-end projects turn concepts into working models. Readers learn the complete workflow from preparing data and building neural networks to training, evaluating, improving, saving, and deploying models, with an introduction to MLOps and production considerations.
Volume 1 forms the foundation of the three-volume Deep Learning from Curiosity to Mastery series. Volume 2 advances into modern architectures and emerging AI frontiers, including CNNs, RNNs and LSTMs, embeddings, attention, Transformers, generative AI, reinforcement learning, explainable AI, neural operators, and Liquid Neural Networks. Volume 3 provides the deeper mathematical foundation for deep learning, including linear algebra, calculus, probability, statistics, optimization, regularization, numerical stability, computational complexity, and mathematical treatments of major neural-network architectures.
Designed for both independent study and instructor-led courses, Volume 1 provides an approachable path from first principles to building, training, evaluating, and deploying neural networks.
Hallo! Ich bin Libroamiko, dein Buchberater.
Wie kann ich dir helfen?