Full metadata
Title
Analyzing Failure Modes of Inscrutable Machine Learning Models
Description
Machine learning models and in specific, neural networks, are well known for being inscrutable in nature. From image classification tasks and generative techniques for data augmentation, to general purpose natural language models, neural networks are currently the algorithm of preference that is riding the top of the current artificial intelligence (AI) wave, having experienced the greatest boost in popularity above any other machine learning solution. However, due to their inscrutable design based on the optimization of millions of parameters, it is ever so complex to understand how their decision is influenced nor why (and when) they fail. While some works aim at explaining neural network decisions or making systems to be inherently interpretable the great majority of state of the art machine learning works prioritize performance over interpretability effectively becoming black boxes. Hence, there is still uncertainty in the decision boundaries of these already deployed solutions whose predictions should still be analyzed and taken with care. This becomes even more important when these models are used on sensitive scenarios such as medicine, criminal justice, settings with native inherent social biases or where egregious mispredictions can negatively impact the system or human trust down the line. Thus, the aim of this work is to provide a comprehensive analysis on the failure modes of the state of the art neural networks from three domains: large image classifiers and their misclassifications, generative adversarial networks when used for data augmentation and transformer networks applied to structured representations and reasoning about actions and change.
Date Created
2022
Contributors
- Olmo Hernandez, Alberto (Author)
- Kambhampati, Subbarao (Thesis advisor)
- Liu, Huan (Committee member)
- Li, Baoxin (Committee member)
- Sengupta, Sailik (Committee member)
- Arizona State University (Publisher)
Resource Type
Extent
137 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.171440
Level of coding
minimal
Cataloging Standards
Note
Partial requirement for: Ph.D., Arizona State University, 2022
Field of study: Computer Science
System Created
- 2022-12-20 12:33:10
System Modified
- 2022-12-20 12:52:47
- 1 year 11 months ago
Additional Formats