Emergent patterns of task-specific neurons in deep neural networks
Name
1237416359-MIT.pdf
Size
2.1 MB
Format
Adobe PDF
Checksum (MD5)
d460436f4ef4bb71ecdc8f984518e618
Author(s)
Dozier, Jamell(Jamell A.)
Advisor(s)
Tomaso Poggio.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
Visual cognition has long been the subject of curiosity within the realm of deep learning. While much research has gone into the development of neural network models that can at times outperform humans, the underlying principles behind truly understanding visual concepts remain elusive. Utilizing a multitask learning paradigm, we first explore the capacity for networks to generalize to understand visual reasoning concepts. We introduce a simplified visual reasoning dataset to train several network architectures, including a recently proposed model built specifically for relational reasoning. We collect the best performing networks and view their behavior on a neuronal level: visualizing task selectivity through patterns of activations from each network layer. Finally, we adjust our focus to a simpler form of visual reasoning involving the extraction of single attributes from attribute compositions. Here, we are able to both visualize and quantify the neuron task selectivity that leads to generalization.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020
Cataloged from student-submitted PDF of thesis.
Includes bibliographical references (pages 69-70).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
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
