Course Finder

Artificial Neural Networks and Deep Learning

Artificial Neural Networks and Deep Learning


Artificial Neural Networks and Deep Learning

About this course

Artificial Neural Networks are programs that write themselves when given an objective, some training data, and abundant computing power. Recently, these programs have brought about a wide array of impressive innovations, such as self-driving cars, face recognition, and human-like speech generators. This course offers you an introduction to Deep Artificial Neural Networks (i.e. “Deep Learning”). With focus on both theory and practice, we cover models for various applications, how they are trained and tested, and how they can be deployed in real-world applications

Syllabus

Syllabus Section A – Fall 2024

Go to syllabus

This is the most recent syllabus for this course

Syllabus Section B – Fall 2024

Go to syllabus

This is the most recent syllabus for this course

Syllabus Section C – Fall 2024

Go to syllabus

This is the most recent syllabus for this course

Pre-requisites

One year of computer science at university level. One of the computer science courses should be in algorithms and data structures. One course in either probability theory, linear algebra, or statistics at university level. Knowledge of programming languages (e.g. in Python/Javascript/Java/C++/Matlab).

Faculty

Daniel Svendsen

Faculty

Ph.D in Electrical Engineering, University of Valencia (2020). Research focus on the incorporation of physical knowledge in machine learning models. Previous experience as a Data Science Consultant to various startups, such as eeSea and Pensure (2020). M.Sc. in Mathematical Modelling and Computation from the Technical University of Denmark (2016). Also taught as a Teaching Assistant in various courses (2015-2016). With DIS since 2021.

Lucian Leahu

Faculty

Ph.D. in Computer Science, Cornell University (2012). Previous experience as Assistant Professor at ITU Copenhagen (2015-2018), ERCIM Postdoctoral Fellow at the Swedish Institute of Computer Science (2012-2013),an and Project Leader in the Media Technology and Interaction Design Department at the Royal Institute of Technology (2014). With DIS since 2019.

Matthias Heumesser

Faculty

Ph.D. in Atmospheric Physics, Marie Skłodowska-Curie Fellow, Technical University of Denmark (2021). Currently leads development of custom car and charger integrations for a smart charging platform as Development Team Lead at True Energy A/S (2022–present). Previous experience developing NLP models for question and implied information detection in emergency calls as Software Developer at Corti (2021–2022). With DIS since 2023.

Lorenzo Belgrano

Faculty

M.Sc. in Mathematical Modelling and Computation, Technical University of Denmark (2019). B.Sc. in Information Engineering, University of Padua (2016). Senior Machine Learning Engineer at Corti (2019–2024). Previous experience implementing deployment pipelines using Docker and Azure ML and developed a FastAPI to request detection to ML models using Tensorflow Serving. With DIS since 2023.