CSMAI19-Artificial Intelligence

Module Provider: School of Mathematical, Physical and Computational Sciences
Number of credits: 10 [5 ECTS credits]
Level:7
Terms in which taught: Spring term module
Pre-requisites:
Non-modular pre-requisites:
Co-requisites:
Modules excluded: CS3AI18 Artificial Intelligence
Current from: 2019/0

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 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. The module will also provide an opportunity for students to develop their Python skills.

Additional outcomes:

The students will become familiar with the potential applications of data artificial intelligence techniques in different domains. They will also learn how to carry out experimental tests for algorithm performance evaluations.

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 lectures per week.

Summative assessment- Examinations:

Summative assessment- Coursework and in-class tests:

One piece of coursework assignment.

Formative assessment methods:

Penalties for late submission:
Penalties for late submission on this module are in accordance with the University policy. Please refer to page 5 of the Postgraduate Guide to Assessment for further information: http://www.reading.ac.uk/internal/exams/student/exa-guidePG.aspx

Assessment requirements for a pass:

A mark of 50% overall.

Reassessment arrangements:

One examination paper of 2 hours.

Additional Costs (specified where applicable):

Last updated: 20 May 2019