Artificial Intelligence is not a single system or tool. It's a collection of different methods that learn, reason, and solve problems in unique ways. Each type of AI has its own strengths, limitations, and data requirements. Learn how these types differ, when to use each, and what tradeoffs are most important in production systems.

Course Objectives

By the end of this course, you will be able do:

• Define and Distinguish Core AI Categories: Describe the major types of AI, including supervised, unsupervised, self-supervised, reinforcement, generative, symbolic, and agentic learning systems.
• Match Use Cases to the Correct Learning Type: Determine which problems fit best with each AI method.
• Differentiate Predictive and Generative Modeling: Recognize the difference between AI that forecasts outcomes and AI that creates new content.
• Recognize Classical Symbolic AI, Search, and Planning: Explain how logic-based systems, rules, and knowledge graphs continue to be essential for clear, auditable, and compliant decision-making.
• Explain Agentic Patterns and Orchestration Describe how modern AI systems coordinate multiple models and tools through planners, retrievers, evaluators, and memory components.
• Evaluate Tradeoffs in Production Environments: Analyze how data volume, labeling effort, latency, interpretability, safety, and cost influence which AI approach is most effective.