Towards an integrated understanding of neural networks
Name
1088414386-MIT.pdf
Description
Full printable version
Size
13.29 MB
Format
Adobe PDF
Checksum (MD5)
31af4cc63d1002c31bc4ab67846477f8
Author(s)
Rolnick, David (David S.)
Advisor(s)
Nir Shavit, Edward S. Boyden, and Max Tegmark.
Date Issued
2018
Publisher
Massachusetts Institute of Technology
Abstract
Neural networks underpin both biological intelligence and modern Al systems, yet there is relatively little theory for how the observed behavior of these networks arises. Even the connectivity of neurons within the brain remains largely unknown, and popular deep learning algorithms lack theoretical justification or reliability guarantees. This thesis aims towards a more rigorous understanding of neural networks. We characterize and, where possible, prove essential properties of neural algorithms: expressivity, learning, and robustness. We show how observed emergent behavior can arise from network dynamics, and we develop algorithms for learning more about the network structure of the brain.
Description
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mathematics, 2018.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 123-136).
Subjects
Mathematics.
MIT Department
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
Persistent DSpace Link
