Topographic VAEs learn Equivariant Capsules

09/03/2021
by   T. Anderson Keller, et al.
9

In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. To accomplish this, we introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. Furthermore, through topographic organization over time (i.e. temporal coherence), we demonstrate how predefined latent space transformation operators can be encouraged for observed transformed input sequences – a primitive form of unsupervised learned equivariance. We demonstrate that this model successfully learns sets of approximately equivariant features (i.e. "capsules") directly from sequences and achieves higher likelihood on correspondingly transforming test sequences. Equivariance is verified quantitatively by measuring the approximate commutativity of the inference network and the sequence transformations. Finally, we demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.

READ FULL TEXT

page 20

page 21

page 22

page 23

page 24

page 25

page 26

page 27

research
02/03/2021

Organization of a Latent Space structure in VAE/GAN trained by navigation data

We present a novel artificial cognitive mapping system using generative ...
research
07/10/2019

Out-of-Distribution Detection Using Neural Rendering Generative Models

Out-of-distribution (OoD) detection is a natural downstream task for dee...
research
01/24/2019

On the Transformation of Latent Space in Autoencoders

Noting the importance of the latent variables in inference and learning,...
research
11/29/2019

Transflow Learning: Repurposing Flow Models Without Retraining

It is well known that deep generative models have a rich latent space, a...
research
06/09/2015

Learning to Linearize Under Uncertainty

Training deep feature hierarchies to solve supervised learning tasks has...
research
10/17/2018

PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences

Given the emerging global threat of antimicrobial resistance, new method...
research
12/23/2020

Analyzing Representations inside Convolutional Neural Networks

How can we discover and succinctly summarize the concepts that a neural ...

Please sign up or login with your details

Forgot password? Click here to reset