Artificial Intelligence is the science of getting computers to do things which, when done by humans, involve the exercise of intelligence. It has been an important strand of Computer Science throughout the lifetime of that discipline, and has exerted a significant influence on other areas of Computer Science as well as on practical applications. This module will provide you with a broad overview of Artificial Intelligence, as well as a more detailed understanding, both practical and theoretical, of selected topics within this area. This module is suitable for any student who has a basic knowledge of computer programming, as well as linear algebra, discrete mathematics, and probability theory.

Pre-requisites: ECM1415 and ECM2418

In this module we aim to provide you with a general introduction to some of the main topics within the broad field of Artificial Intelligence, beginning with an overview of the history and philosophy of AI, then proceeding to a more detailed examination of a range of specific sub-areas, including logic and knowledge representation, searching algorithms, machine learning, and natural language processing.

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

Module Specific Skills and Knowledge:
1 Explain the nature of Artificial Intelligence, its scope, and its limitations;
2 Display competence in a range of Artificial Intelligence tools and techniques;
3 Explain the theoretical basis for a range of Artificial Intelligence methods;
4 Make use of Artificial Intelligence methods in practical applications.
Discipline Specific Skills and Knowledge:
5 Describe a number of different programming paradigms;
6 Learn a variety of computing techniques and apply them to real problems.
Personal and Key Transferable / Employment Skills and Knowledge:
7 Plan and execute a technical report;
8 Adapt existing technical knowledge to learning new methods.

• philosophy of AI: the Turing Test and the Chinese Room, arguments and counter-arguments. Topics from the history of AI: The Dartmouth Conference; early work in reasoning, natural language, and microworlds; the "AI winter"; distributed AI and connectionism; logicism and its detractors, "neats" vs "scruffies"; the fifth generation project; embodied AI and cognitive robotics;
• logic and knowledge representation: recapitulation and further exploration of first-order logic and logic programming. Reasoning strategies. Use of first-order logic as a knowledge representation language;
• searching for solutions: hill-climbing, local search and simplex search (search and optimisation); decision trees (searching databases); minimax algorithm (searching gamespaces); A* (searching maps etc.);
• machine learning: introduction (overview, and successful applications); machine learning algorithms including supervised learning models (kNN, Decision trees, Multi-layer Perceptron) and unsupervised learning (k-means clustering); learning and generalisation;
• natural language processing (NLP): introduction to NLP (overview, history and successful stories), N-Gram language model, bigram and trigram HMM part-of-speech tagging.

None

Reassessment will be by coursework and/or written exam in the failed or deferred element only. For referred candidates, the module mark will be capped at 40%. For deferred candidates, the module mark will be uncapped.

ELE: http://vle.exeter.ac.uk

Reading list for this module: