2 options
Uncertainty estimation toward safe AI / Sangdon Park.
- Format:
- Book
- Thesis/Dissertation
- Author/Creator:
- Park, Sangdon, author.
- Language:
- English
- Subjects (All):
- Computer science.
- Mathematics.
- Artificial intelligence.
- Datasets.
- Experiments.
- Calibration.
- Neural networks.
- Classification.
- Boxes.
- Algorithms.
- Ablation.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Local Subjects:
- Computer science.
- Mathematics.
- Artificial intelligence.
- Datasets.
- Experiments.
- Calibration.
- Neural networks.
- Classification.
- Boxes.
- Algorithms.
- Ablation.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Genre:
- Academic theses.
- Physical Description:
- 1 online resource (197 pages)
- Contained In:
- Dissertations Abstracts International 83-03B.
- Place of Publication:
- [Philadelphia, Pennsylvania] : University of Pennsylvania ; Ann Arbor : ProQuest Dissertations & Theses, 2021.
- Language Note:
- English
- System Details:
- Mode of access: World Wide Web.
- text file
- Summary:
- Safety critical AI systems interact with environments based on inductively learned predictors, which may not be always correct. To complement the incorrect predictions, quantifying uncertainty on predictions is crucial to guarantee the safety of the AI systems. The major challenge of uncertainty quantification is making theoretical guarantees for the correctness of uncertainty estimation in various environments. In this thesis, we propose novel approaches on quantifying uncertainty possibly with correctness guarantees under two major environments: (1) the i.i.d. environment, i.e., where the distributions of learning-time and inference-time are identical, and (2) the covariate shift environment, i.e., where covariate distributions of learning-time and inference-time can be different. In particular, we propose an algorithm to construct a set predictor over labels, i.e., a prediction set, that satisfies a probably approximately correct (PAC) guarantee under the i.i.d. and covariate shift environments, while the prediction set size is small enough to be useful as an uncertainty quantifier. Here, the guarantee on the covariate shift assumes the smoothness of covariate distributions. An alternative way to represent uncertainty is via the confidence of predictors; we also propose an algorithm to estimate the confidence of classifiers that comes with the PAC guarantee under the i.i.d. environment, and we rigorously estimate the confidence under the covariate shift environment. We demonstrate that the proposed approaches are practically useful over various tasks, including image classification, visual object detection, visual object tracking, false medical alarm suppression, state estimation in reinforcement learning, fast deep neural network inference, and safe reinforcement learning.
- Notes:
- Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
- Advisors: Lee, Insup; Bastani, Osbert; Committee members: Daniilidis, Kostas ; Matni, Nikolai; Dobriban, Edgar; Weinberger, Kilian Q.
- Department: Computer and Information Science.
- Ph.D. University of Pennsylvania 2021.
- Local Notes:
- School code: 0175
- ISBN:
- 9798535591179
- Access Restriction:
- Restricted for use by site license.
- This item must not be sold to any third party vendors.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.