Free online courseArtificial Intelligence Masterclass: Search, Logic, Machine Learning and Deep Learning

Course Description

Artificial intelligence is no longer a niche topic: it shapes products, decisions, and the way organizations compete. This free online course helps you build a solid, job-relevant foundation by connecting the classic roots of AI with the methods behind today’s most widely used systems. Instead of treating topics in isolation, you will learn how different AI approaches fit together, when each one is appropriate, and how to reason about their strengths and trade-offs.

You will start by understanding what it means for a system to behave intelligently through the lens of agents, environments, and rational decision-making. From there, you will develop a practical intuition for problem formulation and algorithmic thinking by exploring search, including strategies that balance completeness, optimality, and resource limits. This focus is valuable not only for AI, but also for everyday engineering problem solving: defining states, actions, and goals clearly is a transferable skill.

As you progress, the course moves into game-playing and adversarial reasoning, then broadens to evolutionary computation and genetic approaches, giving you tools for exploring large solution spaces when exact methods are costly. You will also build a rigorous understanding of knowledge-based systems, logical representation, and inference, learning how machines can store facts, express relationships, and derive conclusions in a principled way.

Modern AI depends on uncertainty-aware reasoning, so you will learn how probabilistic models support decision-making in the real world. You will connect probability and utility to decision theory, Markov processes, and sequential decision problems, creating a clear pathway to learning systems that improve with data. The machine learning portion develops core ideas such as classification, decision trees, ensembles, and neural networks, followed by deep learning concepts and practical perspectives on datasets and representation. You will also gain exposure to generative AI and complementary areas including fuzzy systems, NLP, ethics, swarm intelligence, and multi-agent coordination.

Throughout the course, exercises help you verify understanding and turn theory into confidence. By the end, you will be able to speak the language of AI, choose appropriate techniques for common scenarios, and prepare for further study or applied projects in artificial intelligence and machine learning.