Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
Author ORCID Identifier
AccessType
Open Access Dissertation
Document Type
dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Computer Science
Year Degree Awarded
2020
Month Degree Awarded
February
First Advisor
Sridhar Mahadevan
Subject Categories
Artificial Intelligence and Robotics
Abstract
Compositionality is useful to reduce the complexity of machine learning models and increase their generalization capabilities, because new problems can be linked to the composition of existing solutions. Recent work has shown that compositional approaches can offer substantial benefits over a wide variety of tasks, from multi-task learning over visual question-answering to natural language inference, among others. A key variant is functional compositionality, where a meta-learner composes different (trainable) functions into complex machine learning models. In this thesis, I generalize existing approaches to functional compositionality under the umbrella of the routing paradigm, where trainable arbitrary functions are 'stacked' to form complex machine learning models.
DOI
https://doi.org/10.7275/15649011
Recommended Citation
Rosenbaum, Clemens GB, "Dynamic Composition of Functions for Modular Learning" (2020). Doctoral Dissertations. 1865.
https://doi.org/10.7275/15649011
https://scholarworks.umass.edu/dissertations_2/1865
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.