Computational Intelligence - 2019 entry

Computational intelligence is the science of computational systems that are able to perform specific tasks, adapting to particular data. The module will equip you to design and use computational intelligence to solve a variety of problems such as planning, scheduling, optimisation, using a variety of techniques including biologically inspired computational, fuzzy logic, agent-based models and simulation.

Pre-requisite Modules: COM2013 (Data Science Group Project 2); ECM1400; MTH1004

The aim of this module is to introduce and give you practice in some of the main areas of computational intelligence that can be used to solve problems arising in data science. It aims to give you and understanding of the theoretical basis of these methods and their relation to other artificial intelligence techniques. Specifically, it will introduce classical “crisp” logic and knowledge representation before proceeding to fuzzy logic to cope with uncertain and vague processes. Searching and optimisation arise in many contexts and this module aims to introduce you deterministic and stochastic optimisation methods, particularly evolutionary optimisation.

On successful completion of this module, you should be able to:

Module Specific Skills and Knowledge:

1 Explain the nature of Computational Intelligence, its scope, and its limitations;

2 Display competence in a range of Computational Intelligence tools and techniques;

3 Explain the theoretical basis for a range of Computational Intelligence methods;

4 Make use of Computational Intelligence methods in practical applications;

Discipline Specific Skills and Knowledge:

5 Describe a number of different programming paradigms;

6 Learn a variety of data science methods and apply them to real problems;

Personal and Key Transferable / Employment Skills and Knowledge:

7 Plan and write a technical report;

8 Adapt existing technical knowledge to learning new methods.

• Introduction: history and context of computational intelligence, artificial intelligence and related disciplines;

• Logic and knowledge representation: first-order logic and logic programming; reasoning strategies; use of first-order logic as a knowledge representation language;

• Fuzzy logic: measurements and modelling in the face of incomplete knowledge; vagueness and uncertainty. Fuzzy set theory; Dempster-Shafer theory; fuzzy logic operators and process;

• Searching for solutions: hill-climbing, local search and simplex search; decision trees (searching databases); minimax algorithm (searching game spaces); A* (searching maps etc.);

• Evolutionary computation: population-based stochastic search; genetic algorithms, representations and operators; exploration and exploitation;

• Agent-based models and simulation: cellular automata; state-based models; complex systems and emergent behaviour; verification and validation.

Basic Reading:

ELE: http://vle.exeter.ac.uk/

Reading list for this module: