Sandro Skansi – Författare

This stimulating text/reference presents a philosophical exploration of the conceptual foundations of deep learning, presenting enlightening perspectives that encompass such diverse disciplines as computer science, mathematics, logic, psychology, and cognitive science. The text also highlights select topics from the fascinating history of this exciting field, including the pioneering work of Rudolf Carnap, Warren McCulloch, Walter Pitts, Bulcsú László, and Geoffrey Hinton.Topics and features:Provides a brief history of mathematical logic, and discusses the critical role of philosophy, psychology, and neuroscience in the history of AIPresents a philosophical case for the use of fuzzy logic approaches in AIInvestigates the similarities and differences between the Word2vec word embedding algorithm, and the ideas of Wittgenstein and Firth on linguisticsExamines how developments in machine learning provide insights into the philosophical challenge of justifying inductive inferencesDebates, with reference to philosophical anthropology, whether an advanced general artificial intelligence might be considered as a living beingInvestigates the issue of computational complexity through deep-learning strategies for understanding AI-complete problems and developing strong AIExplores philosophical questions at the intersection of AI and transhumanismThis inspirational volume will rekindle a passion for deep learning in those already experienced in coding and studying this discipline, and provide a philosophical big-picture perspective for those new to the field.

This stimulating text/reference presents a philosophical exploration of the conceptual foundations of deep learning, presenting enlightening perspectives that encompass such diverse disciplines as computer science, mathematics, logic, psychology, and cognitive science. The text also highlights select topics from the fascinating history of this exciting field, including the pioneering work of Rudolf Carnap, Warren McCulloch, Walter Pitts, Bulcsú László, and Geoffrey Hinton.Topics and features:Provides a brief history of mathematical logic, and discusses the critical role of philosophy, psychology, and neuroscience in the history of AIPresents a philosophical case for the use of fuzzy logic approaches in AIInvestigates the similarities and differences between the Word2vec word embedding algorithm, and the ideas of Wittgenstein and Firth on linguisticsExamines how developments in machine learning provide insights into the philosophical challenge of justifying inductive inferencesDebates, with reference to philosophical anthropology, whether an advanced general artificial intelligence might be considered as a living beingInvestigates the issue of computational complexity through deep-learning strategies for understanding AI-complete problems and developing strong AIExplores philosophical questions at the intersection of AI and transhumanismThis inspirational volume will rekindle a passion for deep learning in those already experienced in coding and studying this discipline, and provide a philosophical big-picture perspective for those new to the field.

This textbook introduces deep learning in a style that is accessible, rigorous, and grounded in working code. It walks through the most widely used algorithms and architectures step by step, with mathematical derivations kept intuitive and Python examples woven through every chapter. The second edition keeps everything from the first, including convolutional networks, LSTMs, Word2vec, RBMs, DBNs, neural Turing machines, memory networks, and autoencoders. It then covers the systems that have reshaped the field since: generative adversarial networks, the transformer architecture and its attention mechanism, the full training pipeline behind modern large language models (LLMs), prompt engineering with real-life guardrail scenarios, parameter-efficient fine-tuning with LoRA, retrieval-augmented generation with vector databases, knowledge graphs, and agentic AI systems illustrated through an industrial case study.Topics and features:Introduces fundamentals of machine learning and mathematical and computational prerequisites for deep learningDiscusses feed-forward neural networks, convolutional networks, and recurrent architectures, and explores the modifications applicable to any neural networkCovers the transformer architecture from first principles, including self-attention, multi-head attention, positional encoding, and a minimal annotated implementationReviews open research problems, from hallucinations and quadratic scaling to alignment faking and the interpretability of model internalsThis proven, fully revised textbook is written for graduate and advanced undergraduate students of computer science, cognitive science, and mathematics.  It should prove equally valuable for readers in linguistics, logic, philosophy, and psychology.Sandro Skansi is an Associate Professor at the University of Zagreb, Croatia, where he teaches logic, political philosophy, artificial intelligence, and cognitive science. Kristina Šekrst is a research associate at the University of Zagreb and a principal engineer at Preamble AI.