- Tuesday 18 May 2021
- Professor Emanuele Borgonovo, Department of Decision Sciences, Bocconi Institute for Data Science and Analytics, Bocconi University
A growing research activity is developing for increasing interpretability of machine findings. When complex architectures are used, analysts are, in fact, exposed to the black-box effect.
This seminar will review several methods used both in the machine learning and in the simulation community to make the black box more transparent. We will discuss tools such as:
- Partial dependence functions
- Layerwise relevance propagation
- Several local and global sensitivity analysis methods
We will also be proposing new tools along with new findings on popular existing tools.
If you would like to join the oline session, please contact Noriko Stevenson.