Content, progress and pedagogy of the module

This module aims at providing insights into the most foundational architectures of deep learning algorithms within both supervised and unsupervised learning, thus building a strong basis for further exploration of more specific and cutting-edge techniques. Real-world problems that are approached with the techniques covered in this module include the development of advanced recommender systems (marketing), computer vision models (healthcare, economics), powerful unsupervised pattern recognition systems (fraud detection or credit default prediction in finance) and sequence modelling for (attempts of) stock market index prediction.

Upon completion, students will acquire theoretical and practical knowledge, enabling them to understand and apply central techniques and concepts of deep learning approaches as well as the fundamentals of artificial intelligence for analytics. They will be able to select and apply appropriate methods to real-world problems and critically reflect on them.

Learning objectives

Knowledge

The objective is that the student after the module possesses the necessary knowledge on:

• the central concepts within deep learning, the key elements of artificial neural networks and depict their functionality.
• main architectures of supervised and unsupervised deep learning algorithms as well as recent developments in deep learning and artificial intelligence.
• ethical and societal problems concerning the use of artificial intelligence.

Skills

The objective is that the student after the module possesses the necessary skills in:

• selecting and preparing various types of data for use in deep learning environments.
• selecting and constructing different kinds of deep learning architectures (e.g., Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Network) and design an appropriate architecture of the models as well as configure and use large pretrained models (e.g., Transformer models for language processing tasks).
• implementing “correct” training of selected models, including tuning and optimising models, utilising trained models for prediction tasks, and evaluating model performance.

Competences

The objective is that the student after the module possesses the necessary competences in:

• using deep learning techniques to solve business problems in Big Data contexts.
• making informed decisions about the selection of algorithms (also where it is better not to use deep learning/AI techniques at all).
• identifying cases that require particular attention concerning ethical and social consequences of deep learning and AI application.

Type of instruction

For information see § 17.

Exam

Prerequisite for enrollment for the exam

• A prerequisite for participating in the exam is that the student has handed in written material.

Exams