AI AND AI PROGRAMMING - 2017/8
Module code: EEEM005
Electrical and Electronic Engineering
WELLS K Dr (Elec Elec En)
Number of Credits
FHEQ Level 7
Module cap (Maximum number of students)
Overall student workload
Independent Study Hours: 107
Lecture Hours: 33
Laboratory Hours: 10
|Assessment type||Unit of assessment||Weighting|
|Coursework||LAB AND ASSIGNMENT||25%|
|Examination||EXAMINATION - 2HRS||75%|
Neural Network coursework Essay
Prerequisites / Co-requisites
None specifically advised.
This module introduces students to some of the basic ideas and concepts that underlie the development of artificially intelligent machine systems.
Deliver knowledge on the basic ideas and concepts that underlie the development of artificially intelligent machine systems.
|Demonstrate knowledge of the set of methods which would be needed to develop an intelligent system.||K|
|Demonstrate an appreciation of the advantages and limitations of these different methods.||KC|
|Demonstrate ability to apply these methods, and so propose suitable solutions to different problem domains in which an intelligent system can provide useful functionality to aide human activity in solving ‘real world' problems.||KCT|
|Demonstrate ability to implement Prolog programs to solve some of these tasks||KCPT|
C - Cognitive/analytical
K - Subject knowledge
T - Transferable skills
P - Professional/Practical skills
Indicative content includes:
15 Lecture hours including 3 problem classes covering:
Historical Overview - Definition of artificial intelligence (AI).Application areas. General problem solving versus specific knowledge. Complexity.
Heuristic Search - Uninformed versus informed search strategies. Formal properties of A*. Minimax game search, alpha-beta pruning.
Logic and Resolution - Knowledge representation. Propositional and predicate calculus. Inference rules. Clause form. Resolution strategies. Prolog and logic programming.
Uncertainty Reasoning - Probabilistic reasoning and Bayes theorem. Belief networks. Dempster-Shafer theory. Fuzzy logic.
15 lecture hours (approx. 5 hiurs programming and 10 hours Neural Networks) with interspersed problem classes covering:
Basic Prolog - execution model, declarative and procedural meaning, backtracking, arithmetic, list representation, negation as failure and difficulties, simple examples.
Prolog Programming and Techniques - input/output, meta-logical and extra-logical predicates, set predicates, cuts, program development and style, correctness and completeness, Applications
Multi-Layer Perceptrons - Convergence theorem, non-separability, LMS algorithms, steepest descent, back-propagation, generalisation, learning factors.
Radial Basis Function Networks - Multivariable interpolation, regularisation, comparison with MLP, learning strategies.
Self-Organising Systems - Hebbian learning, competitive learning, SOFM, LVQ
Recurrent networks - energy functions, Hopfield net, nonlinear dynamical systems, Liapunov stability, attractors
Methods of Teaching / Learning
The learning and teaching strategy is designed to achieve the aforementioned learning outcomes.
The learning and teaching methods include:
Lectures: 30 hours over 10 weeks, 3 hours per week
Labs: 4 supervised labs teaching basic Prolog skills
Assignment: Programming assignment
Alternative assignment: Neural Network report
The assessment strategy is designed to provide students with the opportunity to demonstrate subject-specific knowledge and how this knowledge can be applied in the design of AI solutions to real world problems.
Thus, the summative assessment for this module consists of:
Prolog Assignment coursework (25%) (address learning outcomes 1-4)
Examination (2Hrs) (75%) (address learning outcomes 1-3)
is provided via feedback gained from the problem classes which take place during scheduled lecture sessions, which can be used to prepare for the summative assessment.
Reading list for AI AND AI PROGRAMMING : http://aspire.surrey.ac.uk/modules/eeem005
Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2017/8 academic year.