Concepts for Quick Prototyping in Artificial Intelligence
4.5 ECTS creditsThe course comprises two parts, a lecture component and a prototype development component.
In the first part, current trends in artificial intelligence are discussed and an introduction to deep learning is provided, with a focus on Convolutional Neural Networks and time series models. Then the course treats the tuning of existing deep learning models, with a focus on the possibilities for adaptation and available methods.
In the second part of the course, students develop a prototype to solve a problem, where the solution must be based on machine learning principles. Students are expected to interpret and document the development process and write a report on the results.
In the first part, current trends in artificial intelligence are discussed and an introduction to deep learning is provided, with a focus on Convolutional Neural Networks and time series models. Then the course treats the tuning of existing deep learning models, with a focus on the possibilities for adaptation and available methods.
In the second part of the course, students develop a prototype to solve a problem, where the solution must be based on machine learning principles. Students are expected to interpret and document the development process and write a report on the results.
Progressive specialisation:
A1F (has second‐cycle course/s as entry requirements)
Education level:
Master's level
Admission requirements:
Computer Science 60 ECTS credits (including Concepts for Machine Learning Practitioners 4.5 ECTS credits) or three years of work experience in the IT sector, plus upper secondary level English 6 or English level 2, or equivalent
Selection:
Selection is usually based on your grade point average from upper secondary school or the number of credit points from previous university studies, or both.