Introduction to Artificial Intelligence
What the exam tests
This domain checks that you can define AI precisely, place ML and DL correctly inside it, recall the historical milestones, describe an intelligent agent's structure, and match AI techniques to real applications instead of to science-fiction robots.
Core concepts
- Definition: AI is the branch of computer science that builds systems able to do tasks that normally need human intelligence - perception, reasoning, learning, language, and decision-making.
- Nesting: DL is a subset of ML, and ML is a subset of AI. ML learns patterns from data instead of following hand-written rules; DL is ML built from many-layered neural networks.
- History anchors: Turing's 1950 paper asking whether machines can think; the 1956 Dartmouth workshop that coined the term artificial intelligence; rule-based expert systems of the 1970s–80s; the AI winters when funding collapsed; the 2012 ImageNet deep-learning breakthrough that restarted the boom.
- Intelligent agent: perceives its environment through sensors, acts through actuators, and selects actions to maximise expected performance. A rational agent does the best it can with the information available.
- Applications: recommendation feeds, spam filtering, voice assistants, medical imaging, crop-disease detection, fraud detection, and driver-assistance systems.
Worked example
A school builds a system that reads a student's past attendance and predicts whether the student will be absent tomorrow. Is it AI, ML, or DL? Reasoning: the system improves from data rather than fixed rules, so it is ML; ML sits inside AI, so it is also AI; the method is logistic regression, a classical model with no deep network, so it is not DL. Answer: AI and ML, but not DL.
Traps that cost marks
- Writing that AI and ML are the same, or that DL is separate from ML.
- Calling an ordinary calculator or a fixed-rule program AI - there is no perception, learning, or adaptive decision-making.
- Dating AI only to 1956 and forgetting Turing (1950) or the AI winters.
- Claiming the Turing Test proves intelligence; it tests imitation of human conversation only.