Module Code - Title:

CE4051 - INTRODUCTION TO DATA ENGINEERING AND MACHINE LEARNING

Year Last Offered:

2023/4

Hours Per Week:

Lecture

1

Lab

2

Tutorial

0

Other

0

Private

7

Credits

6

Grading Type:

N

Prerequisite Modules:

Rationale and Purpose of the Module:

To give students an insight and grounding into data engineering and machine learning and prepare them to take more advanced Artificial Intelligence modules. The module will cover mathematical and coding skills essential to developing machine learning applications in Python and will provide an introduction to more advanced machine learning topics such as modern machine learning platforms, data visualisation and deep learning.

Syllabus:

Students undertaking this module will undertake learning in: a programming language (e.g. Python) for machine learning; numeric support in typical scientific scripting (e.g., Numpy/Scipy); graphics and Scientific Visualization: Using scripting languages to build scientific visualizations (Matplotlib); fundamentals and basic concepts of machine learning algorithms (Perceptron, Logistic Regression, Support Vector Machines, Multi-Layer Perceptron); programming basics for machine learning (Scikitlearn, Pandas); and, applications of machine learning (e.g. inference, image classification, etc)

Learning Outcomes:

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

On successful completion of this module, students will be able to: 1. Understand the key components of machine learning systems. 2. Justify the use of appropriate machine learning approaches for given applications. 3. Apply suitable visualisation, pre-, and post-processing technique. 4. Investigate trends and potential biases in data pertaining to machine learning problems.

Affective (Attitudes and Values)

On successful completion of this module, students will be able to: 1. Defend the machine learning approach adopted in solving given problems. 2. Understand that there is no single machine learner that is best in all cases (the so-called 'No Free Lunch Theorem').

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 with online aspects as well as face-to-face interaction. The content is divided into two-week activities with a submission at the end of every two-week window.

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

Prime Texts:

Sebastian Raschka & Vahid Mirhjalili (2017) Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition , Packt Publishing

Introduction to Machine Learning with Python: A Guide for Data Scientists (2016) Andreas C. Müller and Sarah Guido , O'Reilly

Erwin Kreyszig (2006) ADVANCED ENGINEERING MATHEMATICS , Wiley

Other Relevant Texts:

Brian K. Jones and David M. Beazley (2011) Python Cookbook: Recipes for Mastering Python 3 , O'Reilly

Programme(s) in which this Module is Offered:

MSAIMLTFA - MS ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Semester - Year to be First Offered:

Module Leader:

ciaran.eising@ul.ie