English
Related papers

Related papers: A Geometric Perspective on Autoencoders

200 papers

Autoencoders are neural network formulations where the input and output of the network are identical and the goal is to identify the hidden representation in the provided datasets. Generally, autoencoders project the data nonlinearly onto a…

Signal Processing · Electrical Eng. & Systems 2019-07-10 Debjani Bhowick , Deepak K. Gupta , Saumen Maiti , Uma Shankar

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…

Machine Learning · Statistics 2019-04-15 Aditya Grover , Stefano Ermon

We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a…

Machine Learning · Computer Science 2019-12-10 Nitish Srivastava , Hanlin Goh , Ruslan Salakhutdinov

Aiming for higher-level scene understanding, this work presents a neural network approach that takes a road-layout map in bird's-eye-view as input, and predicts a human-interpretable graph that represents the road's topological layout. Our…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Chenyang Lu , Gijs Dubbelman

Choosing a suitable filtering function for the Mapper algorithm can be difficult due to its arbitrariness and domain-specific requirements. Finding a general filtering function that can be applied across domains is therefore of interest,…

Computational Geometry · Computer Science 2021-02-05 Filip Cornell

High-dimensional datasets often exhibit low-dimensional geometric structures, as suggested by the manifold hypothesis, which implies that data lie on a smooth manifold embedded in a higher-dimensional ambient space. While this insight…

Machine Learning · Computer Science 2025-07-11 Paola Causin , Alessio Marta

Autoencoders are unsupervised machine learning circuits whose learning goal is to minimize a distortion measure between inputs and outputs. Linear autoencoders can be defined over any field and only real-valued linear autoencoder have been…

Neural and Evolutionary Computing · Computer Science 2014-03-19 Pierre Baldi , Zhiqin Lu

We present the self-encoder, a neural network trained to guess the identity of each data sample. Despite its simplicity, it learns a very useful representation of data, in a self-supervised way. Specifically, the self-encoder learns to…

Machine Learning · Computer Science 2023-06-27 Armand Boschin , Thomas Bonald , Marc Jeanmougin

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…

Machine Learning · Computer Science 2016-02-12 Anders Boesen Lindbo Larsen , Søren Kaae Sønderby , Hugo Larochelle , Ole Winther

Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are defined by linear paths in this latent space. However, the…

Machine Learning · Statistics 2019-12-06 Marissa Connor , Christopher Rozell

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Thomas W. Mitchel , Michael Taylor , Vincent Sitzmann

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Machine Learning · Computer Science 2015-06-08 Mathieu Germain , Karol Gregor , Iain Murray , Hugo Larochelle

Homology-based invariants can be used to characterize the geometry of datasets and thereby gain some understanding of the processes generating those datasets. In this work we investigate how the geometry of a dataset changes when it is…

Algebraic Topology · Mathematics 2022-03-17 Jens Agerberg , Wojciech Chacholski , Ryan Ramanujam

This work describes a novel data-driven latent space inference framework built on paired autoencoders to handle observational inconsistencies when solving inverse problems. Our approach uses two autoencoders, one for the parameter space and…

Machine Learning · Computer Science 2026-01-19 Emma Hart , Bas Peters , Julianne Chung , Matthias Chung

There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other. For…

Computer Vision and Pattern Recognition · Computer Science 2024-02-14 Alexandru-Raul Todoran , Marius Leordeanu

A rapidly growing area of research is the use of machine learning approaches such as autoencoders for dimensionality reduction of data and models in scientific applications. We show that the canonical formulation of autoencoders suffers…

Machine Learning · Computer Science 2022-07-28 Andrey A. Popov , Arash Sarshar , Austin Chennault , Adrian Sandu

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN)…

Machine Learning · Computer Science 2023-02-20 Shivam Barwey , Varun Shankar , Venkatasubramanian Viswanathan , Romit Maulik

Explainable numerical representations or latent information of otherwise complex datasets are more convenient to analyze and study. These representations assist in identifying clusters and outliers, assess similar data points, and explore…

Computers and Society · Computer Science 2023-10-11 Deepank Verma , Olaf Mumm , Vanessa Miriam Carlow

Manifold embedding algorithms map high-dimensional data down to coordinates in a much lower-dimensional space. One of the aims of dimension reduction is to find intrinsic coordinates that describe the data manifold. The coordinates returned…

Machine Learning · Statistics 2021-07-30 Samson Koelle , Hanyu Zhang , Marina Meila , Yu-Chia Chen

Choosing the right representation for geometry is crucial for making 3D models compatible with existing applications. Focusing on piecewise-smooth man-made shapes, we propose a new representation that is usable in conventional CAD modeling…

Graphics · Computer Science 2021-02-11 Dmitriy Smirnov , Mikhail Bessmeltsev , Justin Solomon