Page 1 of 1

Module Code - Title:

ET5003 - MACHINE LEARNING APPLICATIONS

Year Last Offered:

2021/2

Hours Per Week:

Lecture

2

Lab

0

Tutorial

1

Other

3

Private

4

Credits

6

Grading Type:

N

Prerequisite Modules:

Rationale and Purpose of the Module:

The aim is to introduce a broad subset of Machine Learning Applications. This module equips students with an understanding of the key principles and methods in the field of Machine Learning. Concepts will be illustrated using existing tool sets and case studies with a focus on the key steps needed such as data preparation and model validation. Students will learn to select, apply, analyse, and critique machine learning algorithms using real world noisy data.

Syllabus:

1. Machine learning algorithms, 2. Models and paradigms for machine learning, 3. Probability calculus 4. Bayesian models, Bayesian linear regression and generalised linear models 5. Natural Language Processing: learning to classify text (bag-of-words, n-gram), topic modelling, Model uncertainty, Model comparison/selection/averaging 6. Bayesian Neural Networks and Deep Neural Networks 7. Bayesian Nonparametric methods (Gaussian processes) 8. Latent and mixture models (clustering), Issues and implications of selecting models for use. 9. Applications

Learning Outcomes:

Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)

Upon successful completion of this module you will be able to: 1. Explain a key set of Machine Learning Algorithms 2. Know which algorithm to apply to a particular data set 3. Demonstrate how to properly evaluate and compare models 4. Explain the differences between traditional machine learning and probabilistic machine learning 5. Analyse the results of machine learning models using posterior probabilities

Affective (Attitudes and Values)

Upon successful completion of this module you will be able to demonstrate: 1. Appreciation the implications of bias in data for machine learning paradigms. 2. Defense of the selection of machine learning paradigms. 3. Response to ethical tensions where they arise as a result of the use of machine learning applications.

Psychomotor (Physical Skills)

N/A

How the Module will be Taught and what will be the Learning Experiences of the Students:

The module will be delivered using a blended learning approach using on-line lectures, labs and tutorials.

Research Findings Incorporated in to the Syllabus (If Relevant):

Prime Texts:

J. Watt, R. Borhanni, & A.K. Katsaggelos (2016) Machine Learning Refined: Foundations, Algorithms and Applications , Cambridge
S. Marsland (2014) Machine Learning: An Algorithmic Perspective , CRC Press
Raschka & Mirjalili (2017) Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition , Packt

Other Relevant Texts:

H. Witten, E. Frank, M. Hall, & C. Pal (2016) Data Mining: Practical machine learning tools and techniques , Morgan , Kaufmann
G. Luger (2009) Artificial Intelligence (6th edition) , Addison-Wesley

Programme(s) in which this Module is Offered:

Semester - Year to be First Offered:

Module Leader:

Enrique.naredo@ul.ie