Physical symmetry enhanced neural networks
Name
1201326165-MIT.pdf
Size
6.05 MB
Format
Adobe PDF
Checksum (MD5)
5e693170ab6b9631ca899f6c0acb6407
Author(s)
Jing, Li,Ph. D.Massachusetts Institute of Technology.
Advisor(s)
Marin Soljacic.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
Artificial Intelligence (AI), widely considered "the fourth industrial revolution", has shown its potential to fundamentally change our world. Today's AI technique relies on neural networks. In this thesis, we propose several physical symmetry enhanced neural network models. We first developed unitary recurrent neural networks (RNNs) that solve gradient vanishing and gradient explosion problems. We propose an efficient parametrization method that requires [sigma] (1) complexity per parameter. Our unitary RNN model has shown optimal long-term memory ability. Next, we combine the above model with a gated mechanism. This model outperform popular recurrent neural networks like long short-term memory (LSTMs) and gated recurrent units (GRUs) in many sequential tasks. In the third part, we develop a convolutional neural network architecture that achieves logarithmic scale complexity using symmetry breaking concepts. We demonstrate that our model has superior performance on small image classification tasks. In the last part, we propose a general method to extend convolutional neural networks' inductive bias and embed other types of symmetries. We show that this method improves prediction performance on lens-distorted image
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Physics, February, 2020
Cataloged from student-submitted PDF version of thesis
Includes bibliographical references (pages 91-99).
Subjects
Physics.
MIT Department
Massachusetts Institute of Technology. Department of Physics
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
