Active learning of regular languages as an approach to neural language models verification.
This work tackles the general problem of verifying the behavior of sequence processing neural networks, specifically neural acceptors and neural language models. The contribution is a framework for extracting formal abstractions of the networks under analysis and verifying whether they satisfy given...
Saved in:
| Main Author: | |
|---|---|
| Format: | doctoralThesis |
| Language: | English |
| Published: |
2024
|
| Online Access: | https://hdl.handle.net/20.500.12008/45940 |
| Tags: |
No Tags, Be the first to tag this record!
|
Similar Items: Active learning of regular languages as an approach to neural language models verification.
- Active Learning of Regular Languages as an Approach to Neural Language Models Verification
- A Congruence-based Approach to Active Automata Learning from Neural Language Models code repository
- Improving the Language Active Learning with Multiagent Systems
- Regular Inference over Recurrent Neural Networks as a Method for Black Box Explainability
- Integrating Social and Emotional Learning in the Foreign Language Classroom
- A predictive model of sovereign investment grade using machine learning and natural language processing