Jan-Tobias Sohns(AG Visual Information Analysis, Prof. Leitte)
hosted by PhD Program in CS @ TU KL
"Decision Boundaries: Feature-Space Exploration of Black Box Classifiers"
For critical processes such as cancer diagnosis or loan approval that rely on machine learning, the trust in a classifier's decision depends on its transparency. As data typically spans many dimensions and the reasoning of contemporary models is incomprehensible, new methods of model inspection need to be developed. Specifically, counterfactuals are an upcoming black box explanation approach, where possible 'What if' scenarios are presented that overturn the result to a desired one. However, the mutability of features depends on the situation, thus current algorithms struggle to find expressive scenarios. Integrating the user into the search process can improve this shortcoming. I developed a visual analytic tool to interactively analyze the mapping of data to decisions and hence explore the feature space for patterns and actionable counterfactuals. Model interpretability is increased by introducing the concept of decision boundaries, i.e. hyper-surfaces that separate the high-dimensional feature space by predicted class, and collating it with human domain knowledge.
|Time:||Monday, 25.01.2021, 15:45|