Study information

Advanced Machine Learning - 2019 entry

MODULE TITLEAdvanced Machine Learning CREDIT VALUE15
MODULE CODEECMM436 MODULE CONVENERUnknown
DURATION: TERM 1 2 3
DURATION: WEEKS
Number of Students Taking Module (anticipated) 6
DESCRIPTION - summary of the module content

***DATA SCIENCE AND DATA SCIENCE WITH BUSINESS STUDENTS ONLY***

In this module, you will learn to analyse large and complex datasets (e.g. images, sequences), creating systems that adapt and improve over time to make predictions from data. You will learn about the most prominent and effective techniques currently employed in state-of-the-art machine learning systems: artificial neural network and mainifold learning. Practical exercises, individual study and group work will consolidate your learning.

Pre-requisite modules: ECMM4434 Machine Learning and Statistics.
Co-requisite modules: None.

AIMS - intentions of the module

This module is intended to advance your knowledge on the design of predictive systems. You will learn how to address classification tasks on complex data such as images, sequences or structured information. You will be introduced to predictive tasks that go beyond classification and regression, such as learning when only partial supervision information is available or when the concept being modelled is not constant in time.

The module will be delivered in an intensive one-week residential block, including lectures and practical work, followed by practical work during the rest of the term. Lectures will be accompanied by data analysis, algorithm implementation and seminar discussions. You will undertake individual coursework to develop predictive models to data of interest in your own organisation.

INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge

1. Apply advanced and complex principles for statistical machine learning to various data analysis tasks including supervised, semi-supervised and transfer learning.
2. Demonstrate competence in handling and encoding image, sequential and non-standard data.
3. Establish the appropriate statistical model for a non-standard learning problem and write software to solve it.

Discipline Specific Skills and Knowledge

4.  Appreciate the importance and difficulty of deploying effective models for complex learning tasks on complex data.
5. Apply complex and advanced modelling techniques to a wide range of problems and domains.

Personal and Key Transferable / Employment Skills and Knowledge

6. Identify the compromises and trade-offs which must be made when translating theory into practice.
7. Critically read research papers.
8. Conduct individual research projects.

 

SYLLABUS PLAN - summary of the structure and academic content of the module

Topics will include:

Neural Networks:

  •  Perceptron algorithm and multi-layer perceptron
  •  Backpropagation
  •  Deep Learning
  •  Recursive Neural Networks
  •  Convolutional Neural Networks
  •  Auto-encoders

Kernel Methods:

  •  Support Vector Machines
  •  Kernel Principal Component Analysis and Kernel K-Means
  •  Kernels for structured data: sequences and graphs

Advanced Learning Problems:

  •  Semi-supervised Learning
  •  Transfer Learning
  •  Online Learning and Concept Drift
LEARNING AND TEACHING
LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)
Scheduled Learning & Teaching Activities 32 Guided Independent Study 118 Placement / Study Abroad 0
DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS
Category Hours of study time Description
Scheduled Learning & Teaching 18 Lectures
Scheduled Learning & Teaching 14 Workshops/Tutorials
Guided Independent Study 34 Project and Coursework
Guided Independent Study 88 Guided Independent Study reading and coursework preparation

 

ASSESSMENT
FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade
Form of Assessment Size of Assessment (e.g. duration/length) ILOs Assessed Feedback Method
Daily Workshops 4 hours per day All  Oral
       
       
       
       

 

SUMMATIVE ASSESSMENT (% of credit)
Coursework 50 Written Exams 0 Practical Exams 50
DETAILS OF SUMMATIVE ASSESSMENT
Form of Assessment % of Credit Size of Assessment (e.g. duration/length) ILOs Assessed Feedback Method
Coursework 50 Project All  Written
In Class Presentation and Report 50 Report All Written
         
         
         

 

DETAILS OF RE-ASSESSMENT (where required by referral or deferral)
Original Form of Assessment Form of Re-assessment ILOs Re-assessed Time Scale for Re-assessment
Coursework Coursework All Within 8 weeks
       
       

 

RE-ASSESSMENT NOTES

Deferral – if you miss an assessment for certificated reasons judged acceptable by the Mitigation Committee, you will normally be either deferred in the assessment or an extension may be granted. The mark given for a re-assessment taken as a result of deferral will not be capped and will be treated as it would be if it were your first attempt at the assessment.

Referral – if you have failed the module overall (i.e. a final overall module mark of less than 50%) you will be required to re-take some or all parts of the assessment, as decided by the Module Convenor. The final mark given for a module where re-assessment was taken as a result of referral will be capped at 50%.

RESOURCES
INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener

Basic reading:

 

ELE: http://vle.exeter.ac.uk/

 

Web based and Electronic Resources:

 

Other Resources:

 

Reading list for this module:

Type Author Title Edition Publisher Year ISBN
Set Shawe-Taylor, J. and Cristianini, N. Kernel methods for pattern analysis Cambridge University Press 2006 521813972
Set Christopher Bishop Pattern Recognition and Machine Learning Springer 2007 978-0387310732
Set Webb, A. Statistical Pattern Recognition 2 Wiley 2002 0-470-84513-9
Set Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2nd Springer 2009 978-0387848570
Set Murphy, K. Machine Learning: A Probabilistic Perspective 1st MIT Press 2012 978-0-262-018029
Set David Barber Bayesian Reasoning and Machine Learning Cambridge University Press 2012 978-0-521-51814-7
CREDIT VALUE 15 ECTS VALUE 7.5
PRE-REQUISITE MODULES ECMM434
CO-REQUISITE MODULES
NQF LEVEL (FHEQ) 7 AVAILABLE AS DISTANCE LEARNING No
ORIGIN DATE Thursday 6th July 2017 LAST REVISION DATE Wednesday 15th May 2019
KEY WORDS SEARCH machine learning, statistics, complex data, artificial neural networks, kernel machines

Please note that all modules are subject to change, please get in touch if you have any questions about this module.