Rare event failure test case generation in Learning-Enabled-Controllers
| Autor: | Janos Sztipanovits, Harsh Vardhan |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Correctness Speedup Computer science business.industry Sample (statistics) Space (commercial competition) Machine learning computer.software_genre Machine Learning (cs.LG) Generative model Reinforcement learning Artificial intelligence Latent variable model business computer Event (probability theory) |
| Popis: | Machine learning models have prevalent applications in many real-world problems, which increases the importance of correctness in the behaviour of these trained models. Finding a good test case that can reveal the potential failure in these trained systems can help to retrain these models to increase the correctness. For a well-trained model, the occurrence of a failure is rare. Consequently, searching these rare scenarios by evaluating each sample in input search space or randomized search would be costly and sometimes intractable due to large search space, limited computational resources, and available time. In this paper, we tried to address this challenge of finding these failure scenarios faster than traditional randomized search. The central idea of our approach is to separate the input data space in region of high failure probability and region of low/minimal failure probability based on the observation made by training data, data drawn from real-world statistics, and knowledge from a domain expert. Using these pieces of information, we can design a generative model from which we can generate scenarios that have a high likelihood to reveal the potential failure. We evaluated this approach on two different experimental scenarios and able to speed up the discovery of such failures a thousand-fold faster than the traditional randomized search. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|