Data Science, Machine Learning and AI

Qualification aims

The module prepares students with the ability to apply object-oriented programming principles, design relational database schemas, and implement neural networks and machine learning algorithms, emphasizing human-centered AI considerations, through skills such as coding in Python, using SQL, and leveraging ML libraries, to efficiently manage data science projects and address complex engineering tasks.

Students can

• apply the principles of object-oriented programming (OOP)
• design efficient relational database schemas
• query and manipulate data using structured query language (SQL)
• implement, train and debug neural networks
• implement machine learning (ML) algorithms
• judge the importance of human-centered artificial intelligence (AI)
• consider fairness, transparency, and ethics in AI

by

• writing and debugging Python code
• understanding bias in data
• creating relational data models and applying normalization rules
• executing commands to create, manipulate, and query tables in a relational database
• understanding backpropagation
• choosing suitable network architectures
• analyzing generative models
• understanding and applying machine learning and artificial intelligence methods and algorithms
• writing code and utilizing ML libraries (such as TensorFlow, PyTorch)
• ascertaining and evaluation correct solutions

to

• lay a foundational understanding of OOP in the context of data science, data engineering, machine learning, and AI
• structure and manage data science projects more efficiently
• organize and manage data effectively and avoid redundancy
• solve practical engineering tasks in classification and prediction
• address complex problems in areas such as image recognition and predictive analytics
• mitigate bias and ensure that machine learning and AI technologies serve a broad spectrum of human needs and values

Module Content

Object oriented Programming for Data Science

• Abstract data types, classes, objects, messages, instance variables, methods, encapsulation, private and public access, class variables, constructors, class interface, class implementation
• Data structures, iterators and containers
• Design, code and test a series of object-oriented programs
• Exception handling
• Function overloading, operator overloading
• Generic types, static and dynamic binding, polymorphism, overloading
• Inheritance: Types of inheritance, construction, destruction

Relational Databases

• Basic terms and architectures of databases
• Database system creation
• Principles of the relational model (relational algebra, query optimization, functional dependencies, data integrity and normalization)
• Data modelling (Entity Relationship Model)
• Implementation using a relational database system as an example
• Database language SQL: DDL, DML, DQL
• Transaction concepts
• Active database concepts and fundamentals of Oracle PL/SQL

Machine Learning and AI

• Image classification: Data-driven approach, k-nearest neighbor, Train/val/test splits, L1/L2 distances, cross-validation
• Linear regression, logistic regression, softmax regression
• Optimization: stochastic gradient descent
• Neural Networks, Backpropagation
• Convolutional Neural Networks: Architectures, convolution / pooling layers
• Understanding and visualizing Convolutional Neural Networks

Bibliography

• Lutz, M.: Programming Python Powerful Object-Oriented Programming (ISBN: 0596158106)
• Gamma, E., Helm, R.: Design Patterns Elements of Reusable Object-Oriented Software (ISBN: 0201633612)
• VanderPlas, J.: Python Data Science Handbook – Essential Tools for Working with Data (ISBN: 9781491912058)
• Geron, A.: Hands-On Machine Learning with Scikit-Learn and TensorFlow Concepts, Tools, and Techniques to Build Intelligent Systems (ISBN: 1491962291)
• Elmasri, R, Navathe, R.: Fundamentals of Database Systems. Pearson, 7th edition, Global Edition, 2016
• Garcia-Molina, Jeffrey D. Ullman, Widom J.: Database Systems: The Complete Book, Pearson, 2008
• Nelli, F.: Python Data Analytics, Springer. 2015
• Moncecchi, G., Garreta, R.: Learning scikit-learn – Machine Learning in Python. 2013
• Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning. MIT press, 2016