Image analysis algorithms typically have many parameters that can be hard to tune.
One strategy to approach this challenge is to automatically run a given algorithm with many parameters (e.g. on a compute cluster) and then check the different outcomes to identify the best parameter set, which could then be used for analysis of further similar data sets.
In this meeting we will discuss different approaches to meta-parameter tuning for image analysis, as it is currently done at EMBL.
The aim of this workshop is to exchange experience and potentially identify common goals for further development.
Bookings
Bookings are closed for this event.