ARTIFICIAL INTELLIGENCE - 2017/8

Module code: COM2028

Module provider

Computer Science

Module Leader

GILLAM L Dr (Computer Sci)

Number of Credits

15

ECT Credits

7.5

Framework

FHEQ Level 5

JACs code

I400

Module cap (Maximum number of students)

N/A

Module Availability

Semester 2

Overall student workload

Independent Study Hours: 106

Lecture Hours: 24

Laboratory Hours: 20

Assessment pattern

Assessment type Unit of assessment Weighting
Practical based assessment LAB ASSIGNMENTS 20
Coursework COURSEWORK PROJECT (INDIVIDUAL) 30
Examination 2 HOUR UNSEEN EXAM 50

Alternative Assessment

N/A

Prerequisites / Co-requisites

Programming experience will be helpful but not essential.

Module overview

Computers have become commonplace in many areas of our lives and are able to accomplish many things that humans would find difficult, if not impossible, to do by their own unaided efforts. Whilst computers can perform many calculations in a very short time they generally do not possess the ability to learn or to reason about novel situations or to process incomplete or uncertain data. They will need knowledge of the environment in which they operate so that they can understand what their sensors are monitoring and so that they can behave rationally. This module demonstrates the basic principles and methods of Artificial Intelligence (AI) and provides the basis for understanding and later choosing the correct tools for building such systems. Applications that motivate the development of Artificial Intelligence technology include intelligent robots, automated navigation for autonomous vehicles, object recognition and tracking, medical diagnosis, language communications and many others. Any application that requires human-like intelligence is an application for Artificial Intelligence.

Module aims

This module aims to demonstrate a variety of techniques for capturing human knowledge and represent it in a computer in a way that enables the machine to learn and reason over the data represented and mimic the human ability to deal with incomplete or uncertain data. This module introduces the range of artificial intelligence elements that future robots or intelligent machines must possess as embedded implementations if they are to behave intelligently.

Learning outcomes

Attributes Developed
Understand the fundamental concepts of statistics required in order to support AI techniques.
Describe methods for acquiring and representing human knowledge.
 Describe techniques for representing acquired knowledge in a way that facilitates automated reasoning over the knowledge.
Describe how AI systems are developed and work.
 Demonstrate the ability to design and implement basic AI techniques.
Explain essential elements in various machine learning and computer vision techniques
Evaluate the use of machine learning and computer vision techniques, highlighting their strengths and weaknesses
Evaluate emerging AI techniques.

Attributes Developed

C - Cognitive/analytical

K - Subject knowledge

T - Transferable skills

P - Professional/Practical skills

Module content


Introduction to probability, Bayes’ Theorem and its applications
Learning

Introduction to Learning
K-Nearest Means
K-Nearest Neighbour
Clustering
Decision Tree
Neural Networks
Support-Vector Machines
Bayesian Classifiers
Normal Distribution and Gaussian Classifiers
Optimisation and Genetic Algorithms


Visual Perception

Feature Extraction
Region Detection and Segmentation
Classification and Pattern Recognition


Natural Language Understanding

Syntax, Semantics and Context Analysis
Probabilistic Language Processing



Methods of Teaching / Learning

There are 12 teaching weeks including revision sessions and one reading week in Semester 2. Each week there will be


2 hour lectures
2 hour lab sessions

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate:

              ·         Ability to design and implement basic computer vision and machine learning techniques.

·         Ability to explain essential elements in various machine learning and computer vision techniques.

·         Ability to appraise scientific literature within the field of Artificial Intelligence

 

Thus, the summative assessment for this module consists of:

·         Completion of weekly lab assignments.

          Each lab assignment should be handed in the following Monday in order to receive timely formative feedback from the lecturer.

          Any improved version of all work must be submitted soon after week 8 for an overall score (see the detailed due date on SurreyLearn).

·         Coursework project report. Deadline: week 10.

·         Unseen exam

 

Formative assessment and feedback

Between week 1-7, students will be guided to work on weekly tasks through lab exercises, which should be submitted through SurreyLearn in order to receive individual feedback.  The solutions to lab tasks and questions will be available after each submission. Students will be able to complete the coursework project successfully once the foundation of the coursework is built through lab exercises. There will also be sessions in the lab targeting questions related to coursework project. Individual Feedback on the coursework project will be given as soon as possible within two weeks or before the exam whichever comes first. Students will be able to gauge their progress through these feedbacks at different stages. 

Reading list

Reading list for ARTIFICIAL INTELLIGENCE : http://aspire.surrey.ac.uk/modules/com2028

Programmes this module appears in

Programme Semester Classification Qualifying conditions
Computer Science BSc (Hons) 2 Compulsory A weighted aggregate mark of 40% is required to pass the module
Computing and Information Technology BSc (Hons) 2 Compulsory A weighted aggregate mark of 40% is required to pass the module
Liberal Arts and Sciences BA (Hons)/BSc (Hons) 2 Optional A weighted aggregate mark of 40% is required to pass the module
Biomedicine with Data Science BSc (Hons) 2 Compulsory A weighted aggregate mark of 40% is required to pass the module
Data Science for Health BSc (Hons) 2 Compulsory A weighted aggregate mark of 40% is required to pass the module

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.