Please log in to watch this conference skillscast.
Machine learning algorithms are a powerful tool for exploiting large data sets in order to model and predict complex system and human behaviour. In this talk Karl will share practical examples where data science techniques can be used to enhance engineering design and control engineering process. By fusing white-box and black-box modelling approaches, you will learn how to exploit both data captured from real-world sensors and representations based on system expertise to develop more flexible and robust models. In particular Karl will show an example where a white-box models can be encoded as a layer within a chain of neural networks to allow efficient computation.
YOU MAY ALSO LIKE:
- An introduction to modelling uncertainty with Gaussian Processes (SkillsCast recorded in May 2016)
- Automating Elaborate-Transform-Load for Busy Data Scientists (SkillsCast recorded in October 2019)
- Apache Druid: the fast, real-time, open-source analytics data store (SkillsCast recorded in September 2019)