Modeling the Geometry of Neural Network Representation Spaces
Neural networks automate the process of representing objects and their relations on a computer, including everything from household items to molecules. New representations are obtained by transforming different instances into a shared representation space, where variations in data can be measured us...
Main Author: | Robinson, Joshua David |
---|---|
Other Authors: | Jegelka, Stefanie |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/152692 |
Similar Items
-
The geometry of representational drift in natural and artificial neural networks.
by: Kyle Aitken, et al.
Published: (2022-11-01) -
Representing Deep Neural Networks Latent Space Geometries with Graphs
by: Carlos Lassance, et al.
Published: (2021-01-01) -
Neural representation of geometry and surface properties in object and scene perception
by: Matthew X. Lowe, et al.
Published: (2017-08-01) -
Representation of affine finite geometries by means of finite vector space :: Ringkasan
by: , KROMODIHARDJO, Kusno
Published: (1982) -
The Neural Representational Space of Social Memory
by: Sarah L. Dziura, et al.
Published: (2019-02-01)