Core Concepts

Explore a diverse array of learning materials, covering the essentials of ML and including university-level courses instructed by AI professionals. These resources provide a fundamental grasp of vital principles in the realm of ML and AI.

Courses

• Machine Learning Specialization (opens in a new tab) by DeepLearning.AI is a comprehensive journey into the heart of ML. Led by industry expert Andrew Ng, offers an immersive exploration of key ML concepts, hands-on projects, and the skills needed to build intelligent systems. Dive into the world of ML, explore its practical applications, and pave the way for a career in this dynamic field. This specialization comprises three courses: Supervised ML: Regression and Classification, Advanced Learning Algorithms and Unsupervised Learning, Recommenders, Reinforcement Learning.

• Google Machine Learning Education (opens in a new tab): Google provides a variety of resources, including foundational courses that cover machine learning basics and core concepts. Guides offer step-by-step walkthroughs for solving common machine learning problems using best practices, while advanced courses teach tools and techniques for addressing a range of machine learning challenges.

Guides

• Machine Learning Mastery: Begin Your Journey Here (opens in a new tab): The common question that often comes my way is: "How do I start?" This all-encompassing guide not only addresses this question by offering insights into what to focus on and cultivating the right mindset but also delves into various subjects. It covers essentials such as mathematics for machine learning, Python programming, deep learning with Keras and PyTorch, natural language processing (NLP), computer vision, and more.

• Machine Learning is Fun! (opens in a new tab): Adam Geitgey's 8-part series covers a comprehensive range of machine learning topics, from basics to advanced concepts. The series includes parts on: ML Fundamentals, Neural Networks, Deep Learning & Convolutional Neural Networks (CNNs), Face Recognition, Language Translation, Speech Recognition, Generative Adversarial Networks (GANs), and Intentionally Tricking Neural Networks. It offers a diverse and enriching learning experience for both beginners and advanced learners.

• Machine Learning for Beginners (opens in a new tab): Microsoft's Azure Cloud Advocates introduce a comprehensive Machine Learning curriculum. Focused on classic machine learning with Scikit-learn, it excludes deep learning, covered in the 'AI for Beginners' course. Pair it with the 'Data Science for Beginners' curriculum for a comprehensive learning experience.

• Scikit-learn Docs (opens in a new tab) provides efficient tools for data mining and analysis, offering diverse ML algorithms for classification, regression, clustering, dimensionality reduction, model selection, and preprocessing tasks.

AI Talks

• Opportunities in AI (opens in a new tab): Andrew Ng's video on AI opportunities is a captivating exploration of the limitless potential within the AI landscape. Gain valuable insights into the transformative power of AI, discover real-world applications, and uncover pathways to harness AI for innovation and growth.

• From Machine Learning to Autonomous Intelligence (opens in a new tab): Yann LeCun delves into how machines can match human and animal efficiency in learning, reasoning, planning, and acquiring representations at various abstraction levels. Jump to 22:30 (opens in a new tab) for insights into AI applications.

Books

• Hands on Machine learing (opens in a new tab) by Aurélien Géron, you'll find a practical approach to machine learning. Dive into ML, grasp essential concepts, work on practical applications, and explore potential R&D directions, all while diving into real-world code examples.

• Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python (opens in a new tab) is a comprehensive guide to using Python for data science, with a focus on scikit-learn for machine learning and PyTorch for deep learning. It covers topics like model evaluation, hyperparameter optimization, and deep learning, providing code examples for hands-on learning.

• Pattern Recognition and Machine Learning (opens in a new tab) by Christopher M. Bishop is an insightful exploration of the core concepts in machine learning. This comprehensive guide delves into algorithms, offering a thorough understanding of pattern recognition and its applications in the evolving landscape of artificial intelligence.

• An Introduction to Statistical Learning (opens in a new tab): As the extent and scale of gathering data expand across nearly every domain, a profound understanding of statistical learning has become indispensable. This book offers a comprehensive and accessible exploration of essential concepts in statistical learning, catering to individuals seeking to harness modern tools for data analysis. Widely recognized as the "Bible of Machine Learning," this book is suitable for a broad audience interested in leveraging contemporary methods for insightful data interpretation.

Additional Reading

• What is the history of artificial intelligence (AI)? (opens in a new tab): It provides a timeline of significant events in the history of AI, encompassing major advancements from the foundational efforts in the early 1900s to the significant leaps achieved in more recent times. For a deeper dive, consider exploring Timeline of artificial intelligence at Wikipedia.

• The Turing Test (opens in a new tab): In 1950, Alan Turing revolutionized the field of AI with his paper "Computing Machinery and Intelligence," introducing the Turing Test to evaluate machine intelligence through human-like interaction. This groundbreaking work profoundly influenced discussions on AI, establishing the foundation for future developments in the field. It sparked extensive discussions and debates in philosophy, cognitive science, and AI. For a brief overview, watch The Turing test: Can a computer pass for a human?

• The Church-Turing Thesis (opens in a new tab) posits that any effectively calculable function can be computed by a Turing machine. Proposed by Alonzo Church and Alan Turing, this foundational concept in computer science and mathematics underlies the universality of computation, asserting the equivalence of various models in expressing computational processes. For a brief overview & simple explanation, watch the video on Turing Machines.