Computer Science

 

ECM3420 - Learning from Data (2012)

Back | Download as PDF
MODULE TITLELearning from Data CREDIT VALUE15
MODULE CODEECM3420 MODULE CONVENERProf Richard Everson (Coordinator)
DURATION: TERM 1 2 3
DURATION: WEEKS 11 weeks
Number of Students Taking Module (anticipated) 11
DESCRIPTION - summary of the module content

Artificially intelligent  machines and software must assimilate data from their environment and make decisions based upon it.  Likewise, we live in a data-rich society and must be able to make sense of complex datasets.  This module will introduce you to machine learning methods for learning from data.  You will learn about the principal learning paradigms from a theoretical point of view and gain practical experience through a series of workshops. The emphasis throughout is on dealing with real data and you will use, modify and write software to implement learning algorithms.  It is often useful to be able to visualise data and you will gain experience of methods of reducing the dimension of large datasets to facilitate visualisation and understanding.

Prerequisite modules: ECM1401 or ECM1408, ECM1701, ECM1707

AIMS - intentions of the module

The goal of artificially intelligent machines requires that machines and software must assimilate data from their environment and make decisions based upon it. This module aims to equip the student with the fundamentals of machine learning in a computer science context. It will provide a thorough grounding in the theory and application of machine learning and statistical techniques for classification, regression and unsupervised methods.  Particular attention is paid to methods for visualising complex datasets.

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

Module Specific Skills and Knowledge:
1 apply principles for statistical pattern recognition to novel data;
2 analyse novel pattern recognition and classification problems, establish models for them and write software to solve them;
3 apply a range of supervised and unsupervised pattern recognition and machine learning techniques to a wide range of problems;
Discipline Specific Skills and Knowledge:
4 state the importance and difficulty of establishing principled models for pattern recognition;
5 use Matlab or other programming languages for scientific analysis and simulation;
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 and report on research papers.

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

Introductory material: Basic ideas of classification, regression and preliminary concepts. Data description. 

Statistical preliminaries: Probability, standard distributions and densities, Bayes rule.

Neural networks: common neural network architectures, MLPs, RBF networks.

Classification and receiver operating characteristic curves, KNN classifiers, linear discriminants, kernel-based classifiers.  

Learning and generalisation: maximum likelihood estimators, Bayesian learning,  optimisation in practice.  

 Unsupervised methods: clustering,  k-means, mixture models and the expectation-maximisation algorithm. 

Dimension reduction and visualisation: PCA, ICA, linear and nonlinear methods for visualisation, MDS and isomap.

Feature extraction: sequential forwards/backwards selection.

 

LEARNING AND TEACHING
LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)
Scheduled Learning & Teaching Activities 42.00 Guided Independent Study 108.00 Placement / Study Abroad
DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS
Category Hours of study time Description
Scheduled Learning & Teaching activities 22 Lectures
Scheduled Learning & Teaching activities 20 Workshops/tutorials
Guided independent study 50 Individual assessed work
Guided independent study 58 Private study

 

ASSESSMENT
FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade

The initial workshop will be formatively assessed.  Other workshops will have formative components.

SUMMATIVE ASSESSMENT (% of credit)
Coursework 40 Written Exams 60 Practical Exams
DETAILS OF SUMMATIVE ASSESSMENT
Form of Assessment % of Credit Size of Assessment (e.g. duration/length) ILOs Assessed Feedback Method
Written exam – closed book 60 1.5 hours 1,2,3,4,6,7 Verbal on request
Coursework – Practical programming assignments 40 50 hours 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-reassessment
All above Written exam (60%) 1,2,3,4,6,7 Last week of August
All above Coursework (40%) All Completed over summer with a deadline of last week of August
       

 

RE-ASSESSMENT NOTES
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


 

Reading list for this module:

Type Author Title Edition Publisher Year ISBN Search
Set Bishop, C Pattern recognition and machine learning Springer 2007 978-0387310732 [Library]
Set Duda and Hart Pattern Classification and Scene Analysis 2nd Wiley 2002 0471056693 [Library]
Set Nabney, Ian T. NETLAB : algorithms for pattern recognition Springer 2001 1852334401 [Library]
Extended Webb, A Statistical Pattern Recognition 2 Wiley 2002 0-470-84513-9 [Library]
CREDIT VALUE 15 ECTS VALUE 7.5
PRE-REQUISITE MODULES ECM1401, ECM1701, ECM1707
CO-REQUISITE MODULES
NQF LEVEL (FHEQ) 3 (NQF level 6) AVAILABLE AS DISTANCE LEARNING No
ORIGIN DATE Monday 12 March 2012 LAST REVISION DATE Wednesday 17 October 2012
KEY WORDS SEARCH None Defined