Module: Foundations of Artificial Intelligence

Module Specifications..

Current Academic Year 2023 - 2024

Please note that this information is subject to change.

Module Title	Foundations of Artificial Intelligence
Module Code	CA686
School	School of Computing
Module Co-ordinator	Semester 1: Mark Humphrys Semester 2: Mark Humphrys Autumn: Mark Humphrys
Module Teachers	Mark Humphrys
NFQ level	9	Credit Rating	7.5
Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

Repeat examination

Description

This module will provide students with a theoretical and practical grounding in the most important foundational topics in Artificial Intelligence, e.g. AI as search, problem solving, machine learning, machine evolution, perceiving and acting.

Learning Outcomes

1. Explain the basic concepts of artificial intelligence, including its philosophical foundations, and present status and future developments.
2. Implement and evaluate search techniques in AI, including constraint satisfaction, heuristic search and adversarial search.
3. Implement and evaluate computational evolution techniques in AI, including genetic algorithms to solve large-dimensional problems.
4. Implement and evaluate machine learning techniques in AI, including some or all of supervised learning, neural networks, knowledge in learning, probabilistic learning, and reinforcement learning.

*Type*	*Hours*	*Description*
Workload	Full-time hours per semester
Lecture	36	No Description
Assignment Completion	24	No Description
Independent Study	127.5	No Description
Total Workload: 187.5

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Introduction to Artificial Intelligence
Brief history of AI, survey of AI main application fields. The state of the art in modern AI including notable applications and successes. Survey of philosophy of AI and its relation to cognitive science. Open issues in AI.

Problem solving in AI
The paradigm of AI problem solving as search in a large statespace. Exhaustive search. Heuristic search. Search strategies (informed and non). Games, constraint satisfaction problems.

Search - Finding satisfactory paths
Depth-first and breadth-first, iterative deepening, local search and heuristic search. Finding optimal paths: branch and bound, dynamic programming, A*. Adversarial search.

Machine evolution
Computational evolution. Genetic algorithms. Codings of genotype. Fitness and reproduction algorithms. Dynamic fitness function. Large dimensional search. Genotype and phenotype.

Machine Learning
Supervised learning. Neural networks. Back propagation. Coding of inputs. Learning policy. Re-play of experiences. Deep learning. Reinforcement learning. Applications of machine learning.

Assessment Breakdown
Continuous Assessment	40%	Examination Weight	60%

Type	Description	% of total	Assessment Date
Course Work Breakdown
Laboratory Portfolio	Complete a series of laboratory exercises and assignments to gain experience of the methods introduced in formal teaching, and to demonstrate that the learning objectives have been met.	40%	n/a

Reassessment Requirement Type
Resit arrangements are explained by the following categories; 1 = A resit is available for all components of the module 2 = No resit is available for 100% continuous assessment module 3 = No resit is available for the continuous assessment component
This module is category 1

Indicative Reading List

Stuart Russell, Peter Norvig: 2016, Artificial Intelligence: A Modern Approach, 3, Pearson, 978-129215396

Other Resources

None

Programme or List of Programmes

CAPD	PhD
CAPM	MSc
CAPT	PhD-track
EEPT	PhD-track
MCM	M.Sc. in Computing

Archives: