On Calibration of Modern Neural Networks [article]

Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q. Weinberger
2017 arXiv   pre-print
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 factors influencing calibration. We evaluate the performance of various post-processing calibration
more » ... hods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling -- a single-parameter variant of Platt Scaling -- is surprisingly effective at calibrating predictions.
arXiv:1706.04599v2 fatcat:ouwx5xxp5rc73o2nmsluedyi6e