← Search

Michael Pfeiffer

2 accepted papers

2021

Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning

ICLR 2021poster

Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used scaling methods underestimate their calibration error, while alternative Histogram Binning (HB) methods often fail to prese…

2016

Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences

NeurIPS 2016oral

Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. Current RNN models are ill suited to process irregularly sampled data triggered by events generated in continuous time by sensors or other neurons. Such data can occur, for examp…