Overview
This course examines the principles, methods, and applications of artificial intelligence, integrating symbolic reasoning with data-driven approaches. Topics include intelligent agents, problem formulation, uninformed and informed search, adversarial search, constraint satisfaction, heuristic design, game playing, knowledge representation, logical and probabilistic inference, Bayesian reasoning, decision-making, and automated planning.
The course also introduces natural language processing, computer vision, supervised and unsupervised learning, reinforcement learning, feature representation, model evaluation, overfitting, generalization, and neural networks. Students address fairness, transparency, privacy, accountability, safety, labor impacts, and bias in AI systems. Laboratories and a team project develop a documented prototype through a reproducible workflow, with emphasis on algorithm selection, computational trade-offs, performance evaluation, interpretation, and communication of limitations.
Learning Outcomes
- Formulate artificial intelligence problems using appropriate state, action, objective, constraint, or data representations.
- Select and implement suitable search, reasoning, planning, and machine-learning algorithms for defined problem classes.
- Analyze the computational complexity, resource requirements, and practical trade-offs of alternative AI methods.
- Evaluate model performance using appropriate metrics, validation procedures, baselines, and error analyses.
- Interpret the outputs, assumptions, and limitations of symbolic, probabilistic, and data-driven AI systems.
- Synthesize a reproducible AI prototype incorporating data preparation, feature representation, implementation, testing, and documentation.
- Assess risks involving fairness, transparency, privacy, accountability, safety, and bias in datasets and AI models.
- Communicate AI methods, results, uncertainties, and limitations effectively to technical and nontechnical audiences.
Timetable
| Type | Length | Frequency | Period |
|---|---|---|---|
| Lecture | 2 hours | Weekly | All semester |
| Lab | 2 hours | Weekly | All semester |
| Tutorial | 1 hour | Fortnightly | All semester |
| Workshop | 2 hours | Fortnightly | Second term |
Assessment Schedule
| Type | Description | Weighting |
|---|---|---|
| Quiz | Quizzes (5 × 2%) | 10.00% |
| Assignment | Algorithm analysis and implementation assignment | 15.00% |
| Test | Practical programming test | 15.00% |
| Capstone | Team AI prototype and documentation | 25.00% |
| Exam | Mid-semester examination | 15.00% |
| Exam | Final examination | 20.00% |
Prerequisites
Teaching Staff & Programs
This course is delivered jointly by faculty from the participating programs listed below. In line with the Douchewater Way, the University of Sexology tailors core instruction directly to each cohort's specific discipline — adapting curriculum to program needs rather than forcing students into a one-size-fits-all model. Learn more about our approach at The Douchewater Way.
