Module Details
The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session. Queries about the module should be directed to the member of staff with responsibility for the module.
Title Advanced Artificial Intelligence
Code COMP219
Coordinator Dr X Huang
Computer Science
Xiaowei.Huang@liverpool.ac.uk
Year CATS Level Semester CATS Value
Session 2021-22 Level 5 FHEQ First Semester 15

Aims

• To equip students with the knowledge about basic algorithms that have been used to enable the AI agents to conduct the perception, inference, and planning tasks;
• To equip students with the knowledge about machine learning algorithms;
• To provide experience in applying basic AI algorithms to solve problems;
• To provide experience in applying machine learning algorithms to practical problems.

Learning Outcomes

(LO1) Ability to explain in detail how the techniques in the perceive-inference-action loop work.

(LO2) Ability to choose, compare, and apply suitable basic learning algorithms to simple applications.

(LO3) Ability to explain how deep neural networks are constructed and trained, and apply deep neural networks to work with large scale datasets.

(LO4) Understand probabilistic graphical models, and is able to do probabilistic inference on the probabilistic graphical models.

(S1) Self-management (readiness to accept responsibility (i.e. leadership), flexibility, resilience, self-starting, appropriate assertiveness, time management, readiness to improve own performance based on feedback/reflective learning.)

(S2) Positive attitude (A 'can-do' approach, a readiness to take part and contribute; openness to new ideas and a drive to make these happen. Employers also value entrepreneurial graduates who demonstrate an innovative approach, creative thinking, bring fresh knowledge and challenge assumptions.)

(S3) Application of numeracy (manipulation of numbers, general mathematical awareness and its application in practical contexts (e.g. measuring, weighing, estimating and applying formulae))

(S4) Computer Science practice

Syllabus
 

Introduction (2 lectures): Introduction to the module and the Overview of Machine Learning.

Learning Basics (4 lectures): Learning Basics, Probability Foundation, Linear Algebra and Python

Traditional Machine Learning Algorithms (10 lectures): Decision Tree, k-nearest neighbour, Linear Regression, Gradient Descent, Naïve Bayes

Deep Learning Algorithms (6 lectures): Functional View, Features, Forward and Backward Training, Convolutional Neural Networks, Tensorflow, Model Evaluation

Probabilistic Graphical Models (6 lectures): Introduction, I-Maps, Reasoning Patterns, D-Separation, Structural Learning

Revision (1 lecture)

Advanced Topics (2 lectures, optional)

Teaching and Learning Strategies

Teaching Method 1 - Lecture
Description:
Attendance Recorded: Not yet decided
Notes: 3 per week during semester

Teaching Method 2 - Laboratory Work
Description:
Attendance Recorded: Not yet decided

Due to Covid-19, in 2021/22, one or more of the following delivery methods will be implemented based on the current local conditions.

(a) Hybrid delivery
Teaching Method 1 - Lecture
Description: Mix of on-campus/on-line synchronous/asynchronous sessions
Teaching Method 2 - Laboratory Work
Description: Mix of on-campus/on-line synchronous/asynchronous sessions

(b) Fully online delivery and assessment
Teaching Method 1 - Lecture
Description: On-line synchronous/asynchronous lectures
Teaching Method 2 - Laboratory Work
Description: On-line synchronous/asynchronous sessions

(c) Standard on-campus delivery
Teaching Method 1 - Lecture
Description: Mix of on-campus/on-line synchronous/asynchronous session s
Teaching Method 2 - Laboratory Work
Description: On-campus synchronous sessions

Teaching Schedule
  Lectures Seminars Tutorials Lab Practicals Fieldwork Placement Other TOTAL
Study Hours 30

     5

     35
Timetable (if known)              
Private Study 115
TOTAL HOURS 150

Assessment
EXAM Duration Timing
(Semester)		 % of
final
mark		 Resit/resubmission
opportunity		 Penalty for late
submission		 Notes
(219) Final Exam There is a resit opportunity. Standard UoL penalty applies for late submission. This is an anonymous assessment. Assessment Schedule (When) :1  2 hours    70       
CONTINUOUS Duration Timing
(Semester)		 % of
final
mark		 Resit/resubmission
opportunity		 Penalty for late
submission		 Notes
(219.1) Coding: Simple Machin Learning Model. Standard UoL penalty applies for late submission. This is an anonymous assessment. Assessment Schedule (When) :Week 6  1 hour    15       
(219.2) Coding: Train Deep Learning Agents. Standard UoL penalty applies for late submission. This is an anonymous assessment. Assessment Schedule (When) :Week 12  1 hour    15       

Recommended Texts
Reading lists are managed at readinglists.liverpool.ac.uk. Click here to access the reading lists for this module.