Module Code - Title:
CE4041
-
ARTIFICIAL INTELLIGENCE
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
N
Prerequisite Modules:
CE4703
Rationale and Purpose of the Module:
To provide the student with a solid theoretical and practical understanding, knowledge and skill in the application of artificial intelligence and expert systems.
This new module is created to provide an appropriate BE/ME masters level code to the level 9 module in AI in ECE department.
This module will be offered to the Master of Engineering in Electronic and Computer Engineering programme using module ID 3301 Artificial Intelligence
Syllabus:
Section (i) - Introduction to Prolog and "Logic Programming"
Rule-based systems and logic programming. The resolution principle, unification & backtracking.
Recursion & iteration. Prolog representation of algorithms. Extra-logical features of Prolog.
Section (ii) - State-Space Search
Use of state-space search in A.I. programming. Representation of problems in state-space form.
Prolog representation of state-spaces. Heuristics. Search strategies: depth-first, breadth-first, hillclimbing, best-first, branch & bound, Algorithm A, Algorithm A*. Admissibility, Monotonicity, Informedness.
Section (iii) - Expert Systems
The structure of an expert system. Knowledge Representation. The inference engine. Inference strategies. Reasoning under uncertainty.
Section (iv) - Neural Networks
Neural models: McCulloch & Pitts, Rosenblatt. Hebbian learning. The Adaline. Multi-layer
Perceptrons & Backpropagation. Associative networks. Competitive networks.
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
1. Use the resolution technique to solve problems stated in terms of predicate logic.
2. Formulate a search problem in terms of an appropriate state-space representation.
3. Apply suitable search algorithms and heuristics to problem solving.
4. Apply neural network techniques to the solution of classification problems.
5. Construct problem-solving programs in a suitable A.I. language such as Lisp or Prolog.
6. Evaluate the current state of the art in artificial intelligence research and applications.
Affective (Attitudes and Values)
N/A
Psychomotor (Physical Skills)
N/A
How the Module will be Taught and what will be the Learning Experiences of the Students:
Lectures/Labs/Tutorials, Self-directed research and project work.
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
Chollet, F. & Watson, M. (2025)
Deep Learning with Python, 3rd edition.
, Manning
Russell, S. & Norvig, P. (2021)
Artificial Intelligence: A Modern Approach, 4th edition.
, Pearson
Other Relevant Texts:
Zhang, A, et al. (2024)
Dive into Deep Learning
, Cambridge
Prince, S.J.D. (2023)
Understanding Deep Learning
, MIT Press
Bishop, C.M. & Bishop, H. (2024)
Deep Learning: Foundations & Concepts
, Springer
Flach. P. (2013)
Machine Learning
, Cambridge
Bishop, C.M. (2006)
Pattern Recognition and Machine Learning
, Springer
Programme(s) in which this Module is Offered:
BEECENUFA - ELECTRONIC AND COMPUTER ENGINEERING
Semester(s) Module is Offered:
Autumn
Module Leader:
Colin.Flanagan@ul.ie