Hello, if you have any need, please feel free to consult us, this is my wechat: wx91due
COMP9414 Artificial Intelligence
Course Details & Outcomes
Course Description
COMP9414 is an introductory course on Artificial Intelligence covering fundamental topics such as autonomous agents, problem solving, optimisation, logic, knowledge representation, reasoning under uncertainty, vision, language processing, machine learning, neural networks and reinforcement learning. The course is taught with an orientation towards machine learning and with a view to practical applications of Artificial Intelligence using Python. Some AI applications that make use of foundational concepts will be demonstrated in lectures and tutorials.
Course Aims
The course aims to provide a foundation for further studies in AI such as COMP4418 Knowledge Representation and Reasoning, COMP9417 Machine Learning and Data Mining, COMP9517 Computer Vision, COMP9434 Robotic Software Architecture, and COMP9444 Neural Networks and Deep Learning. Postgraduate students with more programming experience may consider enrolling in COMP9814, which is the same as the undergraduate AI course COMP3411 (offered in Term 1).
Course Learning Outcomes
| Course Learning Outcomes |
|---|
| CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques |
| CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI algorithms |
| CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas |
| CLO4 : Evaluate the risks of applying AI in business and industry |
| Course Learning Outcomes | Assessment Item |
|---|---|
| CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques |
|
| CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI algorithms |
|
| CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas |
|
| CLO4 : Evaluate the risks of applying AI in business and industry |
|
Learning and Teaching Technologies
Moodle - Learning Management System
Assessments
Assessment Structure
| Assessment Item | Weight | Relevant Dates |
|---|---|---|
|
Assignment 2
Assessment FormatIndividual
|
25% |
Start DateNot Applicable
Due DateWeek 5: 24 June - 30 June
|
|
Assignment 1
Assessment FormatIndividual
|
25% |
Start DateNot Applicable
Due DateWeek 9: 22 July - 28 July
|
|
Exam
Assessment FormatIndividual
|
50% |
Due DateTBA - Exam Period
|
Assessment Details
-
Assignment 2
Assessment Overview
This programming assignment is marked based on its correctness and on programming style and critical analysis. Students can work on the assignment individually or along with a classmate from the same tutorial. In terms of assessment of correctness and style, there will be no differences in works made by 1 or 2 students. However, for the analysis and discussion, both students must participate. It is the student's responsibility to ensure that the submitted code runs on the school environment using the version of Python installed in the labs.
Weighting:
Results 12.5%
Discussion 12.5%Feedback:
Students will receive feedback from tutors during the discussion session. In these sessions, students will demonstrate their code understanding while tutors will provide additional comments on individual students' solutions.
Course Learning Outcomes
- CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
- CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI algorithms
- CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
- CLO4 : Evaluate the risks of applying AI in business and industry
Assignment submission Turnitin type
Not Applicable
-
Assignment 1
Assessment Overview
This programming assignment is marked based on its correctness and on programming style and critical analysis. Students can work on the assignment individually or along with a classmate from the same tutorial. In terms of assessment of correctness and style, there will be no differences in works made by 1 or 2 students. However, for the analysis and discussion, both students must participate. It is the student's responsibility to ensure that the submitted code runs on the school environment using the version of Python installed in the labs.
Weighting:
Results 12.5%
Discussion 12.5%Feedback:
Students will receive feedback from tutors during the discussion session. In these sessions, students will demonstrate their code understanding while tutors will provide additional comments on individual students' solutions.
Course Learning Outcomes
- CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
- CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI algorithms
- CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
- CLO4 : Evaluate the risks of applying AI in business and industry
Assignment submission Turnitin type
Not Applicable
-
Exam
Assessment Overview
The final exam is a 2-hour examination covering all topics in the course.
Course Learning Outcomes
- CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
- CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI algorithms
- CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
- CLO4 : Evaluate the risks of applying AI in business and industry
General Assessment Information
Grading Basis
Standard
Course Schedule
Attendance Requirements
Students are strongly encouraged to attend all classes and review lecture recordings.
General Schedule Information
Week 1 Introduction
1.1 History of AI
1.2 Agents
1.3 Knowledge representation
1.3.1 Feature-based vs iconic representations
1.3.2 Logic
1.3.3 Learning rules
Week 2 Neural Networks
2.1 Neurons - biological and artificial
2.2 Single-layer perceptron
2.3 Linear separability
2.4 Multi-layer networks
2.5 Backpropagation
2.6 Neural engineering methodology
Week 3 Search
3.1 Uninformed search
3.2 Informed search
3.3 Informed vs uninformed
Week 4 Rewards instead of goals
4.1 Elements of reinforcement learning
4.2 Exploration vs exploitation
4.3 The agent-environment interface
4.4 Values functions
4.5 Temporal-difference prediction
Week 5 Metaheuristics
5.1 Asymptotic complexity
5.2 Classes of problems
5.3 Linear programming
5.4 Search space
5.5 Metaheuristics with and without memory
5.6 Population-based methods
Week 6 Recap and consultation
Week 7 Computer vision
7.1 Image processing
7.2 Scene analysis
7.3 Cognitive vision
Week 8 Language processing
8.1 Formal languages
8.1.1 Chomsky’s hierarchy
8.1.2 Grammars
8.2 Regular expressions
8.3. Minimum edit distance and words
8.4 Natural languages: N-gram models
Week 9 Reasoning with uncertain information
9.1 Confidence factors
9.1 Probability and probabilistic inference
9.2 Bayes nets
9.3 Fuzzy logic
Week 10 Human-aligned intelligent robotics
10.1 Human interaction and human-in-the-loop robot learning
10.2 Explainability and interpretability
10.3 Safe robot exploration
10.4 Ethics
Course Resources
Recommended Resources
- Poole, D.L. & Mackworth, A. Artificial Intelligence: Foundations of Computational Agents. Second Edition. Cambridge University Press, Cambridge, 2017.
- Russell, S.J. & Norvig, P. Artificial Intelligence: A Modern Approach. Fourth Edition, Pearson Education, Hoboken, NJ, 2021.
- Sutton, R. & Barto, A. Reinforcement Learning: An Introduction. MIT press. 2018.
- Jurafsky, D. & Martin, J. H. Speech and Language Processing. Stanford. 2023.
- Nilsson, N. J. Artificial intelligence: a new synthesis. Morgan Kaufmann. 1998.
- Aloimonos, Y., & Sandini, G. Principles of Cognitive Vision. In Cangelosi, A., & Asada, M. (Eds.). Cognitive robotics. MIT Press. 2022.