Machine Learning and Artificial Intelligence -

. .

Résumé :
Mastering AI, machine learning, and data science often means piecing together concepts scattered across countless resources, statistics, and visualizations to foundational models and large language models. This book, the result of eight years of effort, brings it all together in one accessible, engaging package. It clarifies artificial intelligence and data science, blending core mathematical principles with a clear, reader-friendly approach. Unlike traditional textbooks that lean heavily on equations and mathematical formalization, the author starts with minimal prerequisites, layering deeper math as the reader progresses. Each concept, algorithm, or model is unpacked through clear, hands-on examples that build the reader's skills step by step. It strikes a balance between theoretical foundations and practical application, serving as both an academic reference and a practical guide. Furthermore, the book uses humor, casual language, and comics to make the challenging concepts and topics relatable and fun. Any resemblance between the jokes and real life is pure coincidence, and no offense is intended. Table of ContentsPart I: Introduction & Preliminary RequirementsChapter 1: Basic Concepts Chapter 2: Visualization Chapter 3: Probability and Statistics Part II: Unsupervised LearningChapter 4: Clustering Chapter 5: Frequent Itemset, Sequence Mining and Information Retrieval Part III: Data EngineeringChapter 6: Feature Engineering Chapter 7: Dimensionality Reduction and Data Decomposition Part IV: Supervised LearningChapter 8: Regression Analysis Chapter 9: Classification Part V: Neural NetworkChapter 10: Neural Networks and Deep Learning Chapter 11: Self-Supervised Deep Learning Chapter 12: Deep Learning Models and Applications (Text, Vision, and Audio) Part VI: Reinforcement LearningChapter 13: Reinforcement Learning Part VII: Other Algorithms and ConceptsChapter 14: Making Lighter Neural Network and Machine Learning Models Chapter 15: Graph Mining Algorithms Chapter 16: Concepts and Challenges of Working with Data...

Biographie:
Reza Rawassizadeh is a professor of Computer Science at Boston University with over a decade of experience in academic research and industrial projects. His scholarly contributions span digital health, ubiquitous technologies, resource-efficient computing, and on-device AI/machine learning. His research emphasizes developing efficient machine learning and AI models tailored for affordable hardware platforms, advancing the democratization of AI....