Two-level Explanations in Music Emotion Recognition: Q&A

Last week my colleague and I spent a week at the ICML conference and presented our work at the Machine Learning 4 Music Discovery workshop. Public speaking is stressful for me, but you can prepare for it. What you can’t really prepare for are the questions afterwards. I thought of possible questions in advance – … Continue reading Two-level Explanations in Music Emotion Recognition: Q&A

Tensorflow CNN and lime on my own cat & dog images

In a recent blog post I evaluated the R package lime on a regression data set. After this I wanted to go deeper (pun not intended ;)) and use lime on more complicated models such as deep neural networks. I have started collecting cat and dog pictures a long time ago with the idea in … Continue reading Tensorflow CNN and lime on my own cat & dog images

Exploring lime on the house prices dataset

Pretty recently I found a paper with the title “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. The topic of interpretability is very important in the times of complex machine learning models and it’s also related to my PhD topic (reliability of machine learning models). Therefore I wanted to play around with … Continue reading Exploring lime on the house prices dataset