This module will cover topics of:



Machine Learning

Anomaly Detection

Prediction

Supervised Techniques and Algorithms

Classification, and regression

Support Vector Machine (SVM), Decision Tree, and Artificial Neural Network (ANN)

Unsupervised Techniques and Algorithms

Clustering, Association

K-means, DBSCAN, HBOS, XBOS

Reinforcement Learning

Evolutionary Algorithm

Data Dimensionality reduction

ML performance evaluation

E.g. Recall, F-measure, and Accuracy





This module will support the development and assessment of the following Core Knowledge, Skills and Behaviours from the DTSP Apprenticeship Standard:

Knowledge

K5 A range of digital technology solution development techniques and tools.

K12 The role of data management systems within Digital and Technology Solutions.

K13 Principles of data analysis for digital and technology solutions.

Skills

S4 Initiate, design, code, test and debug a software component for a digital and technology solution.

S10 Initiate, design, implement and debug a data product for a digital and technology solution.





This module will support the development and assessment of the following Specialist Route Knowledge, Skills and Behaviours from the DTSP Apprenticeship Standard:



Software Engineer

Knowledge

SK21 How to operate at all stages of the software development life cycle and how each stage is applied in a range of contexts. For example, requirements analysis, design, development, testing, implementation.

K26 How to select and apply a range of software tools used in Software Engineering.

Skills

S19 Implement software engineering projects using appropriate software engineering methods, approaches and techniques.

Business Analyst

Knowledge

K43 A range of Business Analysis investigative techniques.

Skills

S39 Recommend and use appropriate software tools to implement Business Analysis tasks and outcomes.

Data Analyst

Knowledge

K54 How to critically analyse, interpret and evaluate complex information from diverse datasets.

K55 Data formats, structures, architectures and data delivery methods including “unstructured” data.

Skills

S49 Apply different types of Data Analysis, as appropriate, to drive improvements for specific business problems.

S52 Apply a range of techniques for analysing quantitative data such as data mining, time series forecasting, algorithms, statistics and modelling techniques to identify and predict trends and patterns in data.

Assignment 1: Practical Assessment

A practical assignment that leads to hands on experience of using AI-purposed libraries and tools as well as developing your own algorithms. You will be expected to analyse a given task scenario (e.g. Digital Health Monitoring, Crowd and Traffic Management, or Smart Homes) or a similar scenario derived from your workplace and to define the business. You will then design, implement, test and document an AI solution to fit the problem. This work will be assessed by demonstration of your practical work.

Assessing Learning Outcomes 1, 2 and 3



Assessing the following Core KSBs:

Knowledge

K5 A range of digital technology solution development techniques and tools.

K13 Principles of data analysis for digital and technology solutions.

Skills

S10 Initiate, design, implement and debug a data product for a digital and technology solution.



Assignment 2: Presentation

A presentation including:

details of the classification and review of Machine Learning techniques and Data Management and approaches taken in the development of your solution to the scenario

demonstration of your AI software solution

Assessing Learning Outcomes 1 & 4

Assessing the following Core KSBs:

Knowledge

K5 A range of digital technology solution development techniques and tools.

K13 Principles of data analysis for digital and technology solutions.

Skill

S10 Initiate, design, implement and debug a data product for a digital and technology solution.

S13 Report effectively to colleagues and stakeholders using the appropriate language and style, to meet the needs of the audience concerned.

1. demonstrate an understanding of Artificial Intelligence (AI) applications, Machine Learning (ML) techniques and Data Mining (DM) approaches through real world examples

Knowledge and Understanding, Learning, Enquiry

2. analyse a scenario, define the business problem and select an appropriate ML technique and DM approach to implement an AI solution to a system task

Analysis, Reflection, Problem Solving

implement a ML model, and presenting logical and coherent written arguments for choices made in relation to ML technique and DM approaches

Problem Solving, Reflection, Application

4. evaluate and compare the possible solutions of the investigated complex problem

Problem Solving, Reflection

The module will be delivered in a Blended Learning Mode consisting of face to face, online and guided learning sessions.



Teaching sessions will blend theory and practical learning and most importantly where possible contextualised in your workplace as part of your apprenticeship. Learners will be introduced to curriculum concepts and ideas and will then be able to apply theory to practical examples. In addition, students will be provided with a range of resources for independent study such as case studies, academic papers and industry case studies. There will be a mixture of practical and theoretical formative (mock or practice) exercises which will help students build knowledge and confidence in preparation for summative (formal) assessment.



The delivery will be delivered as follows:



Module Launch week: 12 hours

There will be a module launch session consisting of up to 12 hours face to face contact time devoted to developing your understanding of the core purpose and assessment of the module. Learners will be presented with details of how the learning will be structure and how to access to the learning materials for the remainder of the module



Structured Learning Sessions: 15 hours

Following the module launch week you will have a further 15 hours of contact time as a class with the module team. This will typically be as 10 x 1.5-hour online classes which will be a combination of activities including lectures, demonstrations, discussions, tutorials and seminars. Some sessions are likely to be in flipped classroom style, where you will be expected to watch online recordings, read materials or respond to practical activities in preparation for active engagement with problem solving in the online session.



1:1 Progress Checks: 1 hour

As a Blended Learner understanding your progress can be a challenge so you are allocated an hour of 1:1 time with your tutor (typically 3 x 20 minute). Some of these may be in small groups if appropriate. These sessions may be used to discuss key topics, troubleshoot salutations, review working drafts etc



Guided Independent Learning: 178 hours

The module leader will provide resources through the virtual learning environment which will include videos and presentations as well as links to useful websites and other resources. Additional academic learning will be achieved through reading around the subject area, module tutors will suggest useful texts, though many others will be suitable and can be found in our e-library. You should also draw on the expertise in your workplace via your workplace mentor and other colleagues. If you require help understanding any of the concepts, you should contact your module tutor for assistance.

As an apprentice you are constantly developing your Digital Skills as part of your substantial role, and this applies to the development of the knowledge for your modules too. In some cases, there will be a significant cross over between the module content and in others less so, depending on the nature of your workplace duties, this will have direct impact on to the number of Independent Learning required.



Within the Independent learning time you will be expected to complete your assignments, as a guide a typical module assignment should take around 60 hours to complete.

Orange Data mining https://orangedatamining.com/

JetBrains PyCharm (IDE for Python)

Numpy (Python library)

Pandas (Python library)

Scikit-learn API, or similar API

Datasets from Kaggle, Weka, MIMIC or similar sources

These are indicative only. Texts are updated on an annual basis and when you start to study this module, you will be referred to an online reading list, currently provided through Keylinks. You are advised not to buy any textbooks for this module without checking the online reading list.



Theobald, A. (2021), Machine Learning for Absolute Beginners: A Plain English Introduction (Third Edition): 1 (Machine Learning with Python for Beginners), Independently published

Geron, A. (2022), Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow 3e: Concepts, Tools, and Techniques to Build Intelligent Systems, O'Reilly Media; 3rd edition

Huyen, C. (2022), Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications, O'Reilly Media; 1st edition

Tombs, N. (2022), Reflections of a Robot: Dialogues on Artificial Intelligence, Independently Published

Bramer, M.A. (2016)¿Principles of data mining.¿3rd edn. London: Springer.

Engelbrecht, A.P. (2007) Computational intelligence: an introduction. 2nd edn. Hoboken, N.J: John Wiley.

Witten, I.H., Frank, E. and Hall, M. (2011)¿Data mining: practical machine learning tools and techniques.¿3rd edn. London; Amsterdam: Morgan Kaufmann.

Raschka, S. (2017) Python machine learning: machine learning and deep learning with Python, scikit-learn, and TensorFlow.

Artificial intelligence (AI) is one of the oldest fields of computer science that strives to understand the essence of intelligence to compose a new intelligent machine that responds like human intelligence. In recent years, AI in modern business has not only made operations faster and more efficient but has also produced increasingly competitive products. This module establishes an understanding of the characteristics and implications which are inherent in the solution of complex, real-world data science and AI-oriented problems. You will learn to critically evaluate and apply different ML and DM techniques for exemplifying data patterns, as well as using ML tools to build an AI software solution.