Full metadata
Title
Methodologies to Improve Fidelity and Reliability of Deep Learning Models for Real-World Deployment
Description
The past decade witnessed the success of deep learning models in various applications of computer vision and natural language processing. This success can be predominantly attributed to the (i) availability of large amounts of training data; (ii) access of domain aware knowledge; (iii) i.i.d assumption between the train and target distributions and (iv) belief on existing metrics as reliable indicators of performance. When any of these assumptions are violated, the models exhibit brittleness producing adversely varied behavior. This dissertation focuses on methods for accurate model design and characterization that enhance process reliability when certain assumptions are not met. With the need to safely adopt artificial intelligence tools in practice, it is vital to build reliable failure detectors that indicate regimes where the model must not be invoked. To that end, an error predictor trained with a self-calibration objective is developed to estimate loss consistent with the underlying model. The properties of the error predictor are described and their utility in supporting introspection via feature importances and counterfactual explanations is elucidated. While such an approach can signal data regime changes, it is critical to calibrate models using regimes of inlier (training) and outlier data to prevent under- and over-generalization in models i.e., incorrectly identifying inliers as outliers and vice-versa. By identifying the space for specifying inliers and outliers, an anomaly detector that can effectively flag data of varying semantic complexities in medical imaging is next developed. Uncertainty quantification in deep learning models involves identifying sources of failure and characterizing model confidence to enable actionability. A training strategy is developed that allows the accurate estimation of model uncertainties and its benefits are demonstrated for active learning and generalization gap prediction. This helps identify insufficiently sampled regimes and representation insufficiency in models. In addition, the task of deep inversion under data scarce scenarios is considered, which in practice requires a prior to control the optimization. By identifying limitations in existing work, data priors powered by generative models and deep model priors are designed for audio restoration. With relevant empirical studies on a variety of benchmarks, the need for such design strategies is demonstrated.
Date Created
2023
Contributors
- Narayanaswamy, Vivek Sivaraman (Author)
- Spanias, Andreas (Thesis advisor)
- J. Thiagarajan, Jayaraman (Committee member)
- Berisha, Visar (Committee member)
- Tepedelenlioğlu, Cihan (Committee member)
- Arizona State University (Publisher)
Topical Subject
Resource Type
Extent
230 pages
Language
eng
Copyright Statement
In Copyright
Primary Member of
Peer-reviewed
No
Open Access
No
Handle
https://hdl.handle.net/2286/R.2.N.187456
Level of coding
minimal
Cataloging Standards
Note
Partial requirement for: Ph.D., Arizona State University, 2023
Field of study: Electrical Engineering
System Created
- 2023-06-07 11:15:56
System Modified
- 2023-06-07 11:16:04
- 1 year 5 months ago
Additional Formats