Vorträge

Treffen Sie uns auf einer Konferenz!

Verschaffen Sie sich einen Überblick, auf welchen Events unsere codecentric-Kollegen als Referenten vertreten sind. Wir würden uns freuen, Sie auf einer Konferenz persönlich begrüßen zu dürfen.

Explaining complex machine learning models with LIME

16.10.2018

Mind Mastering Machines

30 Euston Square, Euston Square, London, Vereinigtes Königreich

Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria. Why a model makes the predictions it makes, however, is generally neglected. But being able to understand and interpret such models can be immensely important for improving model quality, increasing trust and transparency and for reducing bias. Because complex machine learning models are essentially black boxes and too complicated to understand, we need to use approximations.

Shirin GlanderShirin Glander