- Student Records
Programme & Unit Catalogues


CM50263: Artificial intelligence

Follow this link for further information on academic years Academic Year: 2019/0
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 25%, EX 75%
Further information on unit assessment Assessment Detail:
  • Set Exercises (CW 25%)
  • Written Examination (EX 75%)
Further information on supplementary assessment Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Further information on requisites Requisites: Before taking this unit you must take CM50258 OR take CM50109 OR take another programming unit
Further information on descriptions Description: Aims:
To present a detailed introduction to formal artificial intelligence. To establish a practical understanding of intelligence and computation as strategies for problem solving, and the nature of the problems amenable to various established strategies and approaches.

Learning Outcomes:
On completion of this unit, students will be able to:
1. Understand a wide range of AI techniques, their advantages and disadvantages.
2. Appreciate AI as a mechanism to deal with computationally hard problems in a practical manner.
3. Understand the concepts of formal AI and put them into practice.
4. Write small to medium sized programs for aspects of Artificial Intelligence.
5. Critically evaluate state-of-the-art AI applications.

Skills:
Use of IT (T/F,A) Problem solving (T/F,A),Communication (T/F,A), Critical thinking (T/F,A)

Content:
Goals and foundations of AI.
Problem solving (uninformed, heuristic, and adversarial search; constraint satisfaction).
Logical reasoning (propositional logic, first-order logic, logic programming).
Probabilistic reasoning (probability models, Bayesian networks).
Machine learning (possible topics include decision trees, nearest-neighbor methods, reinforcement learning, neural networks, support vector machines, boosting).
State-of-the-art AI applications will be discussed throughout the unit.
Further information on programme availabilityProgramme availability:

CM50263 is Optional on the following programmes:

Department of Computer Science Department of Electronic & Electrical Engineering

Notes: