Neurosymbolic Learning for Robust and Reliable Intelligent Systems
Name
Inala-jinala-PhD-EECS-2022-thesis.pdf
Description
Thesis PDF
Size
2.26 MB
Format
Adobe PDF
Checksum (MD5)
613b92fcbc7aae53ac34587f74eda548
Author(s)
Inala, Jeevana Priya
Advisor(s)
Solar-Lezama, Armando
Date Issued
February 2022
Publisher
Massachusetts Institute of Technology
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
