all AI news
Optimizing Calibration by Gaining Aware of Prediction Correctness
April 22, 2024, 4:42 a.m. | Yuchi Liu, Lei Wang, Yuli Zou, James Zou, Liang Zheng
cs.LG updates on arXiv.org arxiv.org
Abstract: Model calibration aims to align confidence with prediction correctness. The Cross-Entropy CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE loss has intrinsic limitations. For example, for a narrow misclassification, a calibrator trained by the CE loss often produces high confidence on the wrongly predicted class (e.g., a test sample is wrongly classified and its softmax score on the …
abstract arxiv class confidence cross-entropy cs.cv cs.lg entropy example however intrinsic limitations loss narrow prediction stat.ml training truth type
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 14 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
1 day, 14 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 14 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York