module specification

This module provides a comprehensive overview on the use of data and algorithms to imitate how human learn as a branch of Artificial Intelligence (AI). It also provides practical skills using a programming language such as python for working with various tools to build machine learning solutions. The knowledge and skills obtained can be used in many tasks where extracting knowledge and gaining insight from data is of crucial importance for the competitiveness and the effectiveness of the businesses – customer profiling, product recommendations, market trends analysis, cybersecurity, investment monitoring, stock price prediction, etc. Some basic programming skills using languages such as Python or other relevant languages is required.

N/A

Introduction to machine learning, types of learning, problems machine learning can solve [LO1, LO2]

Understanding data and data analysis process, using Python or other capable languages for analysing data. Data structures and control operations for streamline data processing. [LO1, LO3]

Machine learning steps, building your first machine learning model, essential tools and libraries for machine learning and data visualisation using Python or other capable languages. [LO1, LO3, LO4]

Supervised machine learning models such as k-Nearest neighbours, decision trees and Linear Models, Classification and Regression [LO1, LO2]

Learning as optimisation, e.g., Gradient Descent [LO1, LO2]

Unsupervised machine learning models, clustering [LO1, LO2]

Measuring success, model evaluation and Improvement, cross-validation, grid search, confusion matrix [LO1, LO2]

Machine Learning for text data, large language models [LO1, LO2]

Essential tools and libraries for developing and evaluating supervised and unsupervised machine learning using Python or other capable languages. [LO3, LO4]

Neural networks, deep learning, generative AI [LO1, LO2]

Essential tools and libraries for neural networks and deep learning. [LO3, LO4]

Legal, Ethical & Professional Issues and the impact of Machine Learning on society [LO5]

The module will combine lectures, which define the concepts, explain the algorithms and methods, and practical hands-on workshops, which describe the tools and allow the students to apply the methods in hypothetical and real-life scenarios to build and evaluate machine learning solutions. The students will practice working on real and toy datasets using the tools available.

Blended learning: use the university’s VLE and online tools to provide and deliver content, assessment and feedback, to encourage active learning and to enhance students’ engagement and learning experience.

After completing the module, the students should be able to choose suitable methods and available tools and to construct algorithms, programs and components to build machine learning solutions using general programming languages, like Python, and specialised tools for machine learning, such as Python scikit-learn, NumPy, pandas, matplotlib and Keras, TensorFlow libraries.

LO1 Reveal a deep understanding of and demonstrate familiarity with the different methods for machine learning and assess competently their advantages and limitations.

LO2 Develop competence and confidence to make choice of suitable methods and tools for Machine Learning to achieve best possible performance in various business scenarios to drive organisational success.

LO3 Display familiarity with the various tools and technologies for analysis of real-life and toy datasets using programming languages like Python

LO4 Develop competent skills in data visualisation and development and evaluation of machine learning models using tools such as matplotlib and scikit-learn.

LO5 Appreciate and analyse the legal, ethical, and professional Issues of Machine Learning and estimate the impact of Machine Learning on society

      https://londonmet.rl.talis.com/modules/cs7052

Core

Müller AC, Guido S. Introduction to machine learning with Python: a guide for data scientists. O'Reilly Media, Inc. (2016 Sep 26), ISBN: 1449369901, 9781449369903

Ethem Alpaydin. Introduction to Machine Learning. The MIT Press, 4th edition (2020); ISBN: 9780262043793

Kyle Gallatin, Chris Albon. Machine Learning with Python Cookbook. O′Reilly Media, Inc., 2nd Edition (August. 2023). ISBN:  9781098135720

           Additional

Fabio Nelli, Python Data Analytics : With Pandas, NumPy, and Matplotlib, Apress, 3rd Edition 2023, ISBN: 1484295323, 9781484295328

Hui Jiang, Deep Learning in Science, Cambridge University Press, 2021, ISBN: 9781108955652

Machine Learning Fundamentals, A concise Introduction, Cambridge University Press, 2021, ISBN: 9781108938051

Nikhil Ketkar, Deep Learning with Python, A hands-on Introduction, Apress, 2017, ISBN: 9781484227664 

Oswald Campesato, Natural Language Processing Fundamentals for Developers, Mercury Learning and Information, (2021). ISBN:  9781683926566

Igor Milovanovic, Dimitry Foures and Giuseppe Vettigli. Python Data Visualization Cookbook. Packt Publishing; 2nd Revised edition (30 Nov. 2015). ISBN-10: 1784396699

Handbooks

1. Jake Vander Plas. Python Data Science Handbook: Essential Tools for Working with Data, O'Reilly, 2nd Edition (2022); ISBN-10: 1098121228 

Journals:

IEEE Intelligent Systems

IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Neural Networks and Learning Systems

Websites:

Python: https://docs.python.org/3/tutorial/ 

scikit-learn: https://scikit-learn.org/stable/tutorial/index.html 

NLTK: https://www.guru99.com/nltk-tutorial.html 

Matplotlib: https://matplotlib.org/tutorials/index.html 

Pyplot: https://matplotlib.org/tutorials/introductory/pyplot.html 

TensorFlow: https://www.tensorflow.org/tutorials