Neurosymbolic Learning for Robust and Reliable Intelligent Systems
This thesis shows that looking at intelligent systems through the lens of neurosymbolic models has several benefits over traditional deep learning approaches. Neurosymbolic models contain symbolic programmatic constructs such as loops and conditionals and continuous neural components. The symbolic p...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/143249 https://orcid.org/0000-0003-1843-589X |
_version_ | 1811094834040012800 |
---|---|
author | Inala, Jeevana Priya |
author2 | Solar-Lezama, Armando |
author_facet | Solar-Lezama, Armando Inala, Jeevana Priya |
author_sort | Inala, Jeevana Priya |
collection | MIT |
description | This thesis shows that looking at intelligent systems through the lens of neurosymbolic models has several benefits over traditional deep learning approaches. Neurosymbolic models contain symbolic programmatic constructs such as loops and conditionals and continuous neural components. The symbolic part makes the model interpretable, generalizable, and robust, while the neural part handles the complexity of the intelligent systems. Concretely, this thesis presents two classes of neurosymbolic models—state-machines and neurosymbolic transformers and evaluates them on two case studies—reinforcement-learning based autonomous systems and multirobot systems. These case studies showed that the learned neurosymbolic models are human-readable, can be extrapolated to unseen scenarios, and can handle robust objectives in the specification. To efficiently learn these neurosymbolic models, we introduce neurosymbolic learning algorithms that leverage the latest techniques from machine learning and program synthesis. |
first_indexed | 2024-09-23T16:06:14Z |
format | Thesis |
id | mit-1721.1/143249 |
institution | Massachusetts Institute of Technology |
last_indexed | 2024-09-23T16:06:14Z |
publishDate | 2022 |
publisher | Massachusetts Institute of Technology |
record_format | dspace |
spelling | mit-1721.1/1432492022-06-16T03:04:31Z Neurosymbolic Learning for Robust and Reliable Intelligent Systems Inala, Jeevana Priya Solar-Lezama, Armando Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science This thesis shows that looking at intelligent systems through the lens of neurosymbolic models has several benefits over traditional deep learning approaches. Neurosymbolic models contain symbolic programmatic constructs such as loops and conditionals and continuous neural components. The symbolic part makes the model interpretable, generalizable, and robust, while the neural part handles the complexity of the intelligent systems. Concretely, this thesis presents two classes of neurosymbolic models—state-machines and neurosymbolic transformers and evaluates them on two case studies—reinforcement-learning based autonomous systems and multirobot systems. These case studies showed that the learned neurosymbolic models are human-readable, can be extrapolated to unseen scenarios, and can handle robust objectives in the specification. To efficiently learn these neurosymbolic models, we introduce neurosymbolic learning algorithms that leverage the latest techniques from machine learning and program synthesis. Ph.D. 2022-06-15T13:07:14Z 2022-06-15T13:07:14Z 2022-02 2022-03-04T20:48:02.548Z Thesis https://hdl.handle.net/1721.1/143249 https://orcid.org/0000-0003-1843-589X In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
spellingShingle | Inala, Jeevana Priya Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title | Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title_full | Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title_fullStr | Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title_full_unstemmed | Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title_short | Neurosymbolic Learning for Robust and Reliable Intelligent Systems |
title_sort | neurosymbolic learning for robust and reliable intelligent systems |
url | https://hdl.handle.net/1721.1/143249 https://orcid.org/0000-0003-1843-589X |
work_keys_str_mv | AT inalajeevanapriya neurosymboliclearningforrobustandreliableintelligentsystems |