CS3AI18-Artificial Intelligence

Module Provider: School of Mathematical, Physical and Computational Sciences
Number of credits: 10 [5 ECTS credits]
Level:6
Terms in which taught: Spring term module
Pre-requisites:
Non-modular pre-requisites:
Co-requisites:
Modules excluded:
Current from: 2019/0

Module Convenor: Dr Varun Ojha

Email: v.k.ojha@reading.ac.uk

Type of module:

Summary module description:

The main goal of this module is to familiarize students with fundamental algorithms and methods in Artificial Intelligence.

The module aims to provide students with theoretical and practical knowledge of Artificial Intelligence from various techniques and applications.

Aims:

The dramatic growth in killer applications of the Artificial Intelligence (e.g., speech recognition, face recognition, web search, autonomous driving, automatic scheduling, autonomous systems, smart building, robotics) is evident in everyday life. The main goal of the module is to equip you with the algorithms and techniques to tackle new Artificial Intelligence problems you might encounter in life. This module also encourages students to develop a set of professional skills such as the effective use of commercial software.

Assessable learning outcomes:

By the end of the module students should be able to use the main approaches in Artificial Intelligence and to design state-of-the-art Artificial Intelligence algorithms and methods. The students will understand the basic algorithms and techniques of artificial intelligence. Specifically, upon successful completion of the module, students will develop knowledge of:

• Fundamentals of search and planning in AI Rule-based systems.


• Foundation of a satisfiability problem and algorithms for Sat-solving. Reinforcement Learning.


• AI algorithms for Real-world problems (Games, Robotics, Synthetic Biology)

Finally, upon successful completion of the module, students will develop a wide range of practical skills necessary for modeling problem domains, including games, planning and robotics.

Moreover, the module will provide an opportunity for students to develop their Python skills.

Additional outcomes:

Improved programming skills and applied AI through practical work.

Outline content:

• Nature and goals of AI. Application areas.


• Searching state-spaces. Use of states and transitions to model problems.


• A* search algorithm. Use of heuristics in search.


• Constraint Satisfaction Problems.


• Game Trees.


• Markov Decision Processes.


• Reinforcement Learning.


• Bayes' Nets: Representation, Inference and Sampling.


• Decision Networks.


• Value of Perfect Information and Markov Models.


• Hidden Markov Models.


• Naive Bayes.


• Perceptrons.


• Deep Learning.


• Advanced Topics: Robotics.


• Advanced Topics: Programming Cells and Microorganisms.


• Advanced Topics: Games (e.g., ATARI games, DeepMind DQN).

Brief description of teaching and learning methods:

The module consists of 2 lectures per week.

Contact hours:

Ìý	Autumn	Spring	Summer
Lectures		20
Guided independent study:		80
Ìý	Ìý	Ìý	Ìý
Total hours by term		100
Ìý	Ìý	Ìý	Ìý
Total hours for module	100

Summative Assessment Methods:

Method	Percentage
Written exam	30
Project output other than dissertation	70

Summative assessment- Examinations:

One 1.5-hour examination paper in May/June.

Summative assessment- Coursework and in-class tests:

• Final Project (70%)


• Final exam: One 1.5 hour paper comprising module-related questions (30%)

Formative assessment methods:

Penalties for late submission:
The Module Convener will apply the following penalties for work submitted late:

where the piece of work is submitted after the original deadline (or any formally agreed extension to the deadline): 10% of the total marks available for that piece of work will be deducted from the mark for each working day[1] (or part thereof) following the deadline up to a total of five working days;

where the piece of work is submitted more than five working days after the original deadline (or any formally agreed extension to the deadline): a mark of zero will be recorded.

The University policy statement on penalties for late submission can be found at:
You are strongly advised to ensure that coursework is submitted by the relevant deadline. You should note that it is advisable to submit work in an unfinished state rather than to fail to submit any work.

Assessment requirements for a pass:

A mark of 40% overall.

Reassessment arrangements:

One examination paper of 2 hours duration in August/September.Ìý The resit module mark will be the higher of the exam mark (100% exam) and the exam mark plus previous coursework marks (30% exam, 70% coursework).

Additional Costs (specified where applicable):

Last updated: 2 September 2019