COMP9060 - Applied Machine Learning

Module Details

Module Code: COMP9060
Title: Applied Machine Learning
Long Title: Applied Machine Learning
NFQ Level: Expert
Valid From: Semester 1 - 2017/18 ( September 2017 )
Duration: 1 Semester
Credits: 5
Field of Study: 4811 - Computer Science
Module Delivered in: 1 programme(s)
Module Description: This module will provide learners with a comprehensive knowledge of supervised and unsupervised machine learning techniques. It will also equip students with the skills to comprehensively evaluate models and apply appropriate pre-processing methods. The module will also focus on the application of neural networks and deep learning techniques to real-world problems such as image analysis.
 
Learning Outcomes
On successful completion of this module the learner will be able to:
# Learning Outcome Description
LO1 Apply appropriate machine learning methodologies to facilitate pre-processing, dimensionality reduction and model selection.
LO2 Select and apply appropriate machine learning algorithms to datasets from a specific application domain.
LO3 Evaluate the accuracy of predictive models using standard methods.
LO4 Develop and implement machine learning algorithms for building predictive models.
LO5 Apply neural networks and deep learning methods for solving real-world problems.
LO6 Implement and apply optimization algorithms for solving complex problems with a high dimensional search space.
Dependencies
Module Recommendations

This is prior learning (or a practical skill) that is strongly recommended before enrolment in this module. You may enrol in this module if you have not acquired the recommended learning but you will have considerable difficulty in passing (i.e. achieving the learning outcomes of) the module. While the prior learning is expressed as named MTU module(s) it also allows for learning (in another module or modules) which is equivalent to the learning specified in the named module(s).
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this module. You may not earn additional credit for the same learning and therefore you may not enrol in this module if you have successfully completed any modules in the incompatible list.
No incompatible modules listed
Co-requisite Modules
No Co-requisite modules listed
Requirements

This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed. You may not enrol on this module if you have not acquired the learning specified in this section.
No requirements listed
 
Indicative Content
Pre-processing and Evaluation
Application of a standard machine learning pre-processing methodology using techniques such as dimensionality reduction, model selection, feature selection and hyper-parameter optimization. Overview of evaluation methods such as precision, recall, confusion matrices, learning curves, ROC curves.
Classification Algorithms
Building predictive models using Scikit-Learn for solving classification problems. In-depth understanding of algorithms such as linear classification, logistical regression, decision trees, naive bayes, bayesian networks and instance based learning.
Regression Algorithms
Introduction to the area of regression. Produce predictive regression models using Scikit-Learn. In-depth understanding of algorithms such as uni-variate and multi-variate linear regression and ridge regression. Avoid overfitting by using regularization.
Unsupervised Learning Algorithms
Overview of unsupervised learning techniques. Overview of K-Means, density-based and hierarchical clustering techniques. Optimization and distortion cost function. Random initialization and methods of selecting number of clusters such as silhouette plots.
Neural Networks and Deep Learning
Overview of the concept of a neuron and neural networks. Introduction to concept of a neuron and a perceptron. Training a neural network using back-propagation. Introduction to deep neural networks. Building and deploying deep learning neural networks using TensorFlow. Building computational graphs, running tensor flow sessions, visualizing graphs using tensorboard, using optimizers, building, training and evaluating models using TensorFlow, implementing deep learning for problems such as image analysis, sentiment analysis, audio analysis.
Optimization
Introduction to the area of optimization. Categories of optimization such as meta-heuristic and constraint-based optimization. Informed/Uninformed search strategies. Meta-heuristic optimization algorithms. Introduce the concept of heuristic algorithms such as hill climbing, simulated annealing, evolutionary, particle swarm optimization (PSO), etc.
Module Content & Assessment
Assessment Breakdown%
Coursework100.00%

Assessments

Coursework
Assessment Type Project % of Total Mark 40
Timing Week 6 Learning Outcomes 1,2,3,4
Assessment Description
Apply a range of machine learning algorithms to a dataset. Appropriate pre-processing methodologies should be applied and a comprehensive reporting evaluating the performance of the algorithms should be submitted.
Assessment Type Project % of Total Mark 40
Timing Week 10 Learning Outcomes 5
Assessment Description
Apply deep learning neural networks to a complex real-world problem such as image analysis. The findings should be documented.
Assessment Type Project % of Total Mark 20
Timing Week 13 Learning Outcomes 6
Assessment Description
Implement an optimization algorithm for solving a complex problem with a high dimensional search space.
No End of Module Formal Examination
Reassessment Requirement
Coursework Only
This module is reassessed solely on the basis of re-submitted coursework. There is no repeat written examination.

The University reserves the right to alter the nature and timings of assessment

 

Module Workload

Workload: Full Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Delivers the concepts and theories underpinning the learning outcomes. Every Week 2.00 2
Lab Contact Application of learning to case studies and project work. Every Week 2.00 2
Directed Learning Non Contact Student reads recommended papers and practices implementation. Every Week 3.00 3
Total Hours 7.00
Total Weekly Learner Workload 7.00
Total Weekly Contact Hours 4.00
Workload: Part Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Delivers the concepts and theories underpinning the learning outcomes. Every Week 2.00 2
Lab Contact Application of learning to case studies and project work. Every Week 2.00 2
Independent Learning Non Contact Student reads recommended papers and practices implementation. Every Week 2.00 2
Total Hours 6.00
Total Weekly Learner Workload 6.00
Total Weekly Contact Hours 4.00
 
Module Resources
Recommended Book Resources
  • Sebastian Raschka. (2015), Python Machine Learning, 1st. Packt Publishing, [ISBN: 9781783555130].
  • John Hearty. (2016), Advanced Machine Learning with Python, 1st. Packt Publishing, [ISBN: 9781784398637].
Supplementary Book Resources
  • Peter Flach. (2012), Machine Learning: The Art and Science of Algorithms that Make Sense of Data, 1st. Cambridge University Press, [ISBN: 9781107422223].
  • Ethem Alpaydin. (2016), Machine Learning: The New AI, 1st. MIT Press, [ISBN: 9780262529518].
Recommended Article/Paper Resources
  • Pedro Domingos. (2012), A Few Useful Things to Know about Machine Learning, Communications of the ACM, 55.
Other Resources
 
Module Delivered in
Programme Code Programme Semester Delivery
CR_SDAAN_9 Master of Science in Data Science & Analytics 2 Mandatory