DeepAI AI Chat
Log In Sign Up

Topological Autoencoders

06/03/2019
by   Michael Moor, et al.
1

We propose a novel approach for preserving topological structures of the input space in latent representations of autoencoders. Using persistent homology, a technique from topological data analysis, we calculate topological signatures of both the input and latent space to derive a topological loss term. Under weak theoretical assumptions, we can construct this loss in a differentiable manner, such that the encoding learns to retain multi-scale connectivity information. We show that our approach is theoretically well-founded, while exhibiting favourable latent representations on synthetic manifold data sets. Moreover, on real-world data sets, introducing our topological loss leads to more meaningful latent representations while preserving low reconstruction errors.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/13/2017

Deep Learning with Topological Signatures

Inferring topological and geometrical information from data can offer an...
10/17/2019

Mapper Based Classifier

Topological data analysis aims to extract topological quantities from da...
06/06/2022

On the Convergence of Optimizing Persistent-Homology-Based Losses

Topological loss based on persistent homology has shown promise in vario...
09/30/2022

TOAST: Topological Algorithm for Singularity Tracking

The manifold hypothesis, which assumes that data lie on or close to an u...
06/21/2019

Connectivity-Optimized Representation Learning via Persistent Homology

We study the problem of learning representations with controllable conne...
03/03/2022

Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction

Reconstructing 3D objects from 2D images is both challenging for our bra...
06/27/2018

TopoReg: A Topological Regularizer for Classifiers

Regularization plays a crucial role in supervised learning. A successful...