Accessibility statement

Intelligent Systems 2 - COM00024I

« Back to module search

  • Department: Computer Science
  • Module co-ordinator: Dr. Patrik Huber
  • Credit value: 20 credits
  • Credit level: I
  • Academic year of delivery: 2020-21

Module summary

Machine Learning and Optimisation

Module will run

Occurrence Teaching cycle
A Spring Term 2020-21 to Summer Term 2020-21

Module aims

This module advances the IS stream by introducing the basics of machine learning, purely from an optimisation perspective. The range of topics covers linear regression (picking up where Data 1 left off) to decision trees and a simple neural network (leading into advanced machine learning in the third year). Understanding ML requires knowledge of some mathematical concepts that build upon A-level standard mathematics, specifically: Linear Algebra and Continuous Optimisation. This will be taught in-place. Students will see motivating real world problems, the ML techniques required to solve them, the underlying mathematics needed for the technique and their practical implementation. Practicals will be taught using a python-based modern machine learning library such as TensorFlow or PyTorch and so students will gain experience with the declarative programming paradigm (building on the Software stream).

 

Module learning outcomes

 

I201

Define the machine learning paradigm and distinguish it from the wider field of AI

I202

Distinguish supervised from unsupervised learning, parametric from nonparametric learning and classification from regression. Be able to express a classification problem as a regression problem.

I203

Compute partial derivatives and understand the concept of the gradient as a generalisation of the derivative

I204

Express, manipulate and solve systems of linear equations using linear algebra

I205

Apply linear regression and logistic regression with one variable or multiple variables

I206

Optimise multivariate functions using gradient descent

I207

Explain the concept of overfitting and how regularisation can be used to prevent it

I208

Construct a basic neural network and learn its weights via optimisation using the backpropagation algorithm

I209

Identify clusters in data by applying the unsupervised k-means algorithm

I210

Use K-nearest neighbours and decision tree learning for nonparametric classification

I211

Use a modern machine learning library to implement basic machine learning methods as a computational graph and apply them to real datasets

I212

Appreciate the ethical and privacy implications of machine learning such as relying on black box systems without interpretable parameters, learning from biased or crawled publicly available data

Assessment

Task Length % of module mark
Open Examination
INT2 Open Assessment
N/A 50
University - closed examination
INT2 Closed Exam
2 hours 50

Special assessment rules

None

Reassessment

Task Length % of module mark
Open Examination
INT2 Open Assessment
N/A 50
University - closed examination
INT2 Closed Exam
2 hours 50

Module feedback

Feedback is provided through work in practical sessions, and after the final assessment as per normal University guidelines

Indicative reading

Solomon, Justin. Numerical Algorithms. AK Peters/CRC Press, 2015



The information on this page is indicative of the module that is currently on offer. The University is constantly exploring ways to enhance and improve its degree programmes and therefore reserves the right to make variations to the content and method of delivery of modules, and to discontinue modules, if such action is reasonably considered to be necessary by the University. Where appropriate, the University will notify and consult with affected students in advance about any changes that are required in line with the University's policy on the Approval of Modifications to Existing Taught Programmes of Study.