Internal

CSMAINU: Artificial Intelligence and Machine Learning

CSMAINU: Artificial Intelligence and Machine Learning

Module code: CSMAINU

Module provider: Computer Science; School of Mathematical, Physical and Computational Sciences

Credits: 20

Level: Postgraduate Masters

When you'll be taught: Semester 2

Module convenor: Dr Nachiketa Chakraborty, email: n.chakraborty@reading.ac.uk

NUIST module lead: Yunzhi Huang, email: huang_yunzhi@nuist.edu.cn

Pre-requisite module(s): It is preferable that students have experience in Python before taking this module. (Open)

Co-requisite module(s):

Pre-requisite or Co-requisite module(s):

Module(s) excluded:

Placement information: NA

Academic year: 2024/5

Available to visiting students: No

Talis reading list: No

Last updated: 27 June 2024

Overview

Module aims and purpose

The aim of the module is to introduce students to current methods in artificial intelligence (AI) and machine learning (ML) covering supervised, unsupervised, reinforcement and deep learning. Students will learn how to apply these methods to real-life problems using Python programming language. 

AI is a core component of computer science, aiming at developing intelligent agents that mimic human’s cognitive capability in learning, reasoning, and problem solving. As a branch of AI, ML has recently gained huge attention from technology giants (Google, Facebook, Microsoft, IBM, etc.) and achieved impressive progress in performing many 'human' tasks such as playing games, image recognition, and natural language processing. The recent wave of AI and ML development has already led to significant industrial applications such as self-driving cars and Industry 4.0. Undertaking the module will enable students to contribute to the development of future technologies. 

Students will also be able to demonstrate their abilities in: 

  • formulating research problems;  
  • writing technical reports; and  
  • utilising knowledge and skills to continue learning and adapting to new data science technologies. 

Module learning outcomes

By the end of the module, it is expected that students will be able to:

  1. Understand the main concepts of modern artificial intelligence (AI) and machine learning (ML);
  2. Critically evaluate and practice a range of ML algorithms, tools and frameworks for developing AI solutions;
  3. Apply the learned algorithms, tools and frameworks to solve real-life problems; and
  4. Demonstrate their abilities in formulating research problems, writing technical reports and utilising knowledge and skills to continue learning and adapting to new data science technologies.

Module content

The module will cover the following topics:

  • Artificial Intelligence (AI) and Machine Learning (ML) concepts and tools
  • Programming for AI and ML
  • Data visualisation and pre-processing
  • Algorithms for clustering, classification and prediction
  • Deep Learning
  • Image Processing
  • Information Retrieval and Natural Language Processing
  • Search algorithms
  • Agent Technology and Game Theory
  • Reinforcement Learning

Recommended reading:

  • Sebastian Raschka, Python Machine Learning, 3rd ed.
  • François Chollet, Deep Learning with Python, 2nd ed.
  • D. Jurafsky & J. H. Martin, Speech and Language Processing, 3rd ed.
  • S. Russell & P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed.

Structure

Teaching and learning methods

Material will be delivered via lectures and practical classes on a weekly basis. Additional resources will be available on Blackboard for self-study. A substantial part of the learning process will take place while working on a coursework, which asks students to propose their own unique problem to resolve with a dataset, which is then carried through to implementation tailored to that problem. Continual feedback will be given to student as they develop their projects. 

Study hours

At least 48 hours of scheduled teaching and learning activities will be delivered in person, with the remaining hours for scheduled and self-scheduled teaching and learning activities delivered either in person or online. You will receive further details about how these hours will be delivered before the start of the module.


 Scheduled teaching and learning activities  Semester 1  Semester 2  Summer
Lectures 24
Seminars
Tutorials
Project Supervision
Demonstrations
Practical classes and workshops 24
Supervised time in studio / workshop
Scheduled revision sessions
Feedback meetings with staff
Fieldwork
External visits
Work-based learning


 Self-scheduled teaching and learning activities  Semester 1  Semester 2  Summer
Directed viewing of video materials/screencasts
Participation in discussion boards/other discussions
Feedback meetings with staff
Other
Other (details)


 Placement and study abroad  Semester 1  Semester 2  Summer
Placement
Study abroad

Please note that the hours listed above are for guidance purposes only.

 Independent study hours  Semester 1  Semester 2  Summer
Independent study hours 152

Please note the independent study hours above are notional numbers of hours; each student will approach studying in different ways. We would advise you to reflect on your learning and the number of hours you are allocating to these tasks.

Semester 1 The hours in this column may include hours during the Christmas holiday period.

Semester 2 The hours in this column may include hours during the Easter holiday period.

Summer The hours in this column will take place during the summer holidays and may be at the start and/or end of the module.

Assessment

Requirements for a pass

Students need to achieve an overall module mark of 50% to pass this module.

Summative assessment

Type of assessment Detail of assessment % contribution towards module mark Size of assessment Submission date Additional information
Set exercise Problem-solving exercise 50 3,000 words. 20 hours. Semester 2, Week 9 A problem-solving coursework which involves finding a data set, formulating a problem, building machine learning models, evaluating the models, and reporting the solution and results.
In-person written examination Exam 50 2 hours Semester 2, Weeks 17-19 Answer 3 out of 4 questions

Penalties for late submission of summative assessment

The Support Centres will apply the following penalties for work submitted late:

Assessments with numerical marks

  • where the piece of work is submitted after the original deadline (or any formally agreed extension to the deadline): 10% of the total marks available for that piece of work will be deducted from the mark for each working day (or part thereof) following the deadline up to a total of three working days;
  • the mark awarded due to the imposition of the penalty shall not fall below the threshold pass mark, namely 40% in the case of modules at Levels 4-6 (i.e. undergraduate modules for Parts 1-3) and 50% in the case of Level 7 modules offered as part of an Integrated Masters or taught postgraduate degree programme;
  • where the piece of work is awarded a mark below the threshold pass mark prior to any penalty being imposed, and is submitted up to three working days after the original deadline (or any formally agreed extension to the deadline), no penalty shall be imposed;
  • where the piece of work is submitted more than three working days after the original deadline (or any formally agreed extension to the deadline): a mark of zero will be recorded.

Assessments marked Pass/Fail

  • where the piece of work is submitted within three working days of the deadline (or any formally agreed extension of the deadline): no penalty will be applied;
  • where the piece of work is submitted more than three working days after the original deadline (or any formally agreed extension of the deadline): a grade of Fail will be awarded.

The University policy statement on penalties for late submission can be found at: https://www.reading.ac.uk/cqsd/-/media/project/functions/cqsd/documents/qap/penaltiesforlatesubmission.pdf

You are strongly advised to ensure that coursework is submitted by the relevant deadline. You should note that it is advisable to submit work in an unfinished state rather than to fail to submit any work.

Formative assessment

Formative assessment is any task or activity which creates feedback (or feedforward) for you about your learning, but which does not contribute towards your overall module mark.

Weekly practical exercises (some may be in the form of groupwork) will be used as formative assessment. Feedback on weekly practical exercises will be given to students which will act as feedforward for the coursework assessments. 

Reassessment

Type of reassessment Detail of reassessment % contribution towards module mark Size of reassessment Submission date Additional information
In-person written examination Exam 100 3 hours During the NUIST resit period Answer 4 out of 6 questions

Additional costs

Item Additional information Cost
Computers and devices with a particular specification
Required textbooks
Specialist equipment or materials
Specialist clothing, footwear, or headgear
Printing and binding
Travel, accommodation, and subsistence

THE INFORMATION CONTAINED IN THIS MODULE DESCRIPTION DOES NOT FORM ANY PART OF A STUDENT'S CONTRACT.

Things to do now