flâneur — a map of the web's best reading

On Calibration of Modern Neural Networks

proceedings.mlr.press · 573 words · saved by 1 readers

Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover...

On Calibration of Modern Neural Networks Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q. Weinberger Proceedings of the 34th International Conference on Machine Learning , PMLR 70:1321-1330, 2017. Abstract Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important facto

Explore this link on the map →

related reading