course: 2AMM15

The course covers the principles and engineering aspects of machine learning, from data collection to designing robust and trustworthy machine learning systems. Upon completion of the course, students should have a solid understanding of how practical machine learning algorithms and systems work, be able to write programs that build predictive models from training data, and properly evaluate machine learning models in the real world. They should also be able to construct and optimize complex machine learning pipelines and deep learning architectures, and do this in an efficient way using modern machine learning techniques.

Details

Level:

Master

Target audience:

<p><span style="color: rgb(45, 59, 69); font-family: &quot;Lato Extended&quot;, Lato, &quot;Helvetica Neue&quot;, Helvetica, Arial, sans-serif; font-size: 16px;">This course requires a solid mathematical background, especially linear algebra and statistics, as well as programming experience.&nbsp;</span><span style="color: rgb(45, 59, 69); font-family: &quot;Lato Extended&quot;, Lato, &quot;Helvetica Neue&quot;, Helvetica, Arial, sans-serif; font-size: 16px;">We also expect f</span><span style="color: rgb(45, 59, 69); font-family: &quot;Lato Extended&quot;, Lato, &quot;Helvetica Neue&quot;, Helvetica, Arial, sans-serif; font-size: 16px;">amiliarity with Python programming and basic use of Python for data science and scientific programming.</span></p>

Quartile:

Q2

Lecturers:

Joaquin Vanschoren

More information (external)