English
Related papers

Related papers: The dynamics of representation learning in shallow…

200 papers

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Alexander Bauer , Shinichi Nakajima , Klaus-Robert Müller

This paper proposes a theoretical framework on the mechanism of autoencoders. To the encoder part, under the main use of dimensionality reduction, we investigate its two fundamental properties: bijective maps and data disentangling. The…

Machine Learning · Computer Science 2022-12-13 Changcun Huang

Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences…

Machine Learning · Statistics 2018-07-31 Arnu Pretorius , Steve Kroon , Herman Kamper

Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We…

Machine Learning · Statistics 2017-04-25 Jason Tyler Rolfe

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…

Machine Learning · Statistics 2011-10-27 Jasper Snoek , Ryan Prescott Adams , Hugo Larochelle

We propose a nonlinear manifold learning technique based on deep convolutional autoencoders that is appropriate for model order reduction of physical systems in complex geometries. Convolutional neural networks have proven to be highly…

Computational Physics · Physics 2021-07-19 John Tencer , Kevin Potter

The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for…

Computer Vision and Pattern Recognition · Computer Science 2019-02-04 Ya Ju Fan

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but…

Machine Learning · Computer Science 2019-05-15 Daniel Kunin , Jonathan M. Bloom , Aleksandrina Goeva , Cotton Seed

Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervised paradigm, i.e., reconstruction. Existing studies mainly…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Jianzhang Zheng , Hao Shen , Jian Yang , Xuan Tang , Mingsong Chen , Hui Yu , Jielong Guo , Xian Wei

Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize…

Machine Learning · Computer Science 2018-12-13 Michael Tschannen , Olivier Bachem , Mario Lucic

Model reduction of high-dimensional dynamical systems alleviates computational burdens faced in various tasks from design optimization to model predictive control. One popular model reduction approach is based on projecting the governing…

Dynamical Systems · Mathematics 2018-08-24 Francisco J. Gonzalez , Maciej Balajewicz

We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance…

Machine Learning · Computer Science 2019-05-29 Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by…

Machine Learning · Computer Science 2026-01-28 Qipeng Zhan , Zhuoping Zhou , Zexuan Wang , Li Shen

We develop data-driven methods incorporating geometric and topological information to learn parsimonious representations of nonlinear dynamics from observations. The approaches learn nonlinear state-space models of the dynamics for general…

Machine Learning · Computer Science 2025-03-28 Ryan Lopez , Paul J. Atzberger

Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes.…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Alasdair Newson , Andrés Almansa , Yann Gousseau , Saïd Ladjal

Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lower-dimensional manifold. Recent work by Dai and Wipf (2020)…

Machine Learning · Computer Science 2022-05-19 Frederic Koehler , Viraj Mehta , Chenghui Zhou , Andrej Risteski

Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep…

Machine Learning · Computer Science 2021-01-06 Fenglei Fan , Mengzhou Li , Yueyang Teng , Ge Wang

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward way to map n-dimensional data in input space to a lower m-dimensional representation space and back. The…

Machine Learning · Computer Science 2021-11-16 Viktoria Schuster , Anders Krogh

Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input…

Machine Learning · Statistics 2015-04-09 Kishore Konda , Roland Memisevic , David Krueger