Gauge theory and twins paradox of disentangled representations

06/24/2019
by   X. Dong, et al.
0

Achieving disentangled representations of information is one of the key goals of deep network based machine learning system. Recently there are more discussions on this issue. In this paper, by comparing the geometric structure of disentangled representation and the geometry of the evolution of mixed states in quantum mechanics, we give a fibre bundle based geometric picture of disentangled representation which can be regarded as a kind of gauge theory. From this perspective we can build a connection between the disentangled representations and the twins paradox in relativity. This can help to clarify some problems about disentangled representation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/12/2019

Evaluating Disentangled Representations

There is no generally agreed upon definition of disentangled representat...
research
08/08/2018

Towards Learning Fine-Grained Disentangled Representations from Speech

Learning disentangled representations of high-dimensional data is curren...
research
08/26/2021

A Tutorial on Learning Disentangled Representations in the Imaging Domain

Disentangled representation learning has been proposed as an approach to...
research
02/14/2018

Learning Deep Disentangled Embeddings with the F-Statistic Loss

Deep-embedding methods aim to discover representations of a domain that ...
research
06/20/2019

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Motivated by the need to audit complex and black box models, there has b...
research
05/31/2017

Unsupervised Learning of Disentangled Representations from Video

We present a new model DrNET that learns disentangled image representati...
research
04/19/2018

Learning Disentangled Representations of Texts with Application to Biomedical Abstracts

We propose a method for learning disentangled sets of vector representat...

Please sign up or login with your details

Forgot password? Click here to reset