Module Handbook AML

Course introduction

Teacher contact info

Learning Outcomes

Module Delivery

Assessments

Assessment criteria

Assessment offences

Module HandbookApplied Machine Learning

Learning Resources

Module specification

Year 2021/22

Welcome to Applied Machine Learning

Course Introduction

Applied Machine Learning employs the coding skills covered previously (“Programming in R”) in the development of machine learning algorithms. The present module also informs the three-term Research Project in which students are expected to deploy the techniques and algorithms developed herein. As such, we discuss: data in the wild, data cleaning, data visualization, data structure, machine learning, and predictions from models.

Teacher contact info

Dr Paul Haworth

Hello, I am the Subject Leader for Engineering, Computing, Maths & Science at the Lancaster International Study Centre. I have a PhD in Pure Mathematics and I have been teaching for over 20 years.

Knowledge & understanding

Module Learning Outcomes

a.) Demonstrate knowledge and understanding of the relationship between data structure and approaches to modelling. b.) Demonstrate knowledge and understanding of model building and evaluation.

Subject specific

c) Demonstrate appropriate choice of data visualization and presentation for the effective communication of complex scientific ideas. d) Apply a critical understanding and awareness of the Data Processing Cycle: Collection, Preparation, Input, Processing, Output, and Storage. e) Produce scientific documents in Markdown which include appropriate sectioning, citations, bibliography, formulae and diagrams.

Topic Content Data Frames in R Data ‘in the wild’ Data cleaning Missing values Visualization using the ggplot package What is Machine Learning? Time Series Introduction White Noise Random Walks Lags and Correlation Auto-Regressive Models Model fitting and Residuals Moving Average Models Stationarity ARIMA and SARIMA models Back-testing and auto-fitting Neural Networks What is a Neural Network? Neurons Activation Functions Loss Functions Back Propagation Classification Problems Entropy Feature Importance

Module delivery

TEACHING, LEARNING + ASSESSMENT ACTIVITIES STUDY HOURS

• Lecture Style delivery 10 hours
• Seminars and workshops 40 hours
• Self-directed study 100 hours
• TOTAL 150 hours (15 credits

Assessments

Final module assessment

This project will consist of a set of data analysis problems. you will select one of the problems to respond to. Data sets and appropriate references will be provided. Students will be expected to produce a markdown report which details: the data used, any data preparation required, the selected model / machine learning algorithm, model testing, and code used.

100%

Learning outcomes - a,b,c,d,e,f

Key skills - Critically evaluate and reflect on data analysis

Employability skills -

In order to pass the module, students must achieve a minimum of 40% overall in the summative assessments. Progression will be based on the achievement of the agreed progression grade. Formative Assessment and Feedback Formative assessment will take place during seminar discussions and review of weekly task submissions. Oral feedback will be given at regular intervals as part of the seminar format, and written feedback will be provided on all areas of assessment with specific guidance for further skill development. Students will be assessed on their knowledge and understanding of the module content in one end of module project. This project will consist of a set of data analysis problems. Students will select one of the problems to respond to. Data sets and appropriate references will be provided. Students will be expected to produce a markdown report which details: the data used, any data preparation required, the selected model / machine learning algorithm, model testing, and code used. Student’s work will be assessed in 3 areas: 1) Quality of report structure, 2) Quality of data handling, data representation, and data discussion, 3) Quality of model building, testing, and conclusions drawn.

Assessment Critera

Academic impropriety

Assessment offences

It is important that you are aware of your responsibilites when sitting module assessments Please make sure that you have read the student handbook and the academic rules

Main course text

Learning Resources

This is the main text that you should read during your studies in this module. We will refer to this text each week, and you will need to read a chapter from this book each week related to the content being taught. You must make sure you do the required reading before the lessons so that you have an understanding of the concepts and content that will be covered, and you can engage in the discussion. Required reading: .Burger, S. (2018). Introduction to Machine Learning with R: rigorous mathematical analysis. Beijing; Boston: O’reilly.

Recommended resouces

Zumel, N., Mount, J., Howard, J. and Thomas, R. (2020). Practical data science with R. Shelter Island, Ny: Manning Publications Company. Ciaburro, G. and Balaji Venkateswaran (2017). Neural networks with R : smart models using CNN, RNN, deep learning, and artificial intelligence principles. Birmingham, UK: Packt Publishing. Recommended reading: Wickham, H. and Grolemund, G. (2017). R for data science : import, tidy, transform, visualize, and model data. Beijing: O’reilly. Useful electronic sources (links to): https://www.datacamp.com/

Module specification