Talk at European Symposium on Artificial Neural Networks (ESANN)

I just had my talk at the prestigious ESANN conference in Bruge. I talked about my very first paper “Effcient Accuracy Estimation for Instance-Based Incremental Active Learning” that directly got accepted and I got great feedback at the discussion round. I had a great time at the conference, awesome food and I’ve met a lot of inspiring colleagues. Thank you all!

Abstract: Stimating system’s accuracy is crucial for applications of incremental learning. In this paper, we introduce the Distogram Estimation (DGE) approach to estimate the accuracy of instance-based classifiers. By calculating relative distances to samples it is possible to train an online regression model, capable of predicting the classifier’s accuracy on unseen data. Our approach requires only a few supervised samples for training and can instantaneously be applied on unseen data afterwards. We evaluate our method on five benchmark data sets and for a robot object recognition task. Our algorithm clearly outperforms two baseline methods both for random and active selection of incremental training examples.