CSMAI21-Artificial Intelligence and Machine Learning

Module Provider: School of Mathematical, Physical and Computational Sciences
Number of credits: 20 [10 ECTS credits]
Level:7
Terms in which taught: Spring term module
Pre-requisites:
Non-modular pre-requisites:
Co-requisites:
Modules excluded:
Current from: 2021/2

Module Convenor: Dr Yevgeniya Kovalchuk
Email: y.kovalchuk@reading.ac.uk

Type of module:

Summary module description:

This module covers the topic of artificial intelligence and machine learning.

Aims:

The aim of the module is to introduce students to current methods in artificial intelligence and machine learning.

Assessable learning outcomes:

Students will be able to:

• Understand the classic and fundamental algorithms of artificial intelligence and the modern machine learning methods, including shallow and deep Artificial Neural Networks.


• Acquire knowledge of artificial intelligence techniques such as problem solving, search, reasoning, planning, learning, and perception.


• Determine appropriate machine learning methods for supervised and unsupervised problems.


• Understand and apply the process of training and making predictions with neural networks.


• Determine the appropriate neural network architecture for a particular problem.


• Apply multiple classes of neural networks to real world problems involving images and text.

Additional outcomes:

Students will gain familiarity with modern machine learning and neural networks libraries with hands-on activities.

Outline content:

The module covers foundational topics in relevant artificial intelligence and machine learning algorithms:

• AI goals and applications areas.


• Problem Solving


• Search and Reasoning


• Probabilistic Classifier.


• Support Vector Machines


• Neural Networks and Deep Learning.


• Backpropagation


• Stochastic gradient descent


• Feedforward and recurrent arch itectures


• Convolutional neural networks


• Generative adversarial networks


• Capsule networks


• Unsupervised LearningÌýÌý


• Reinforcement Learning.


• Applications


• Image Classifications


• Natural Language Processing: Text Classification and Text Generation

Brief description of teaching and learning methods:

The module consists of lectures and weekly guided practical classes that implement methods covered in the lectures.

Summative assessment- Examinations:

One 2-hour examination paper in May/June.

Summative assessment- Coursework and in-class tests:

One project-based assignment.

Formative assessment methods:

Feedback in practical classes.

Penalties for late submission:

The below information applies to students on taught programmes except those on Postgraduate Flexible programmes. Penalties for late submission, and the associated procedures, which apply to Postgraduate Flexible programmes are specified in the policy 􀀓Penalties for late submission for Postgraduate Flexible programmes􀀔, which can be found here: