English
Related papers

Related papers: Bilinear autoencoders find interpretable manifolds

200 papers

Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. pairwise distances…

Machine Learning · Computer Science 2018-09-14 Tao Yang , Georgios Arvanitidis , Dongmei Fu , Xiaogang Li , Søren Hauberg

Deep neural networks have reshaped modern machine learning by learning powerful latent representations that often align with the manifold hypothesis: high-dimensional data lie on lower-dimensional manifolds. In this paper, we establish a…

Machine Learning · Computer Science 2025-06-09 Nico Pelleriti , Max Zimmer , Elias Wirth , Sebastian Pokutta

The ability of neural networks to represent more features than neurons makes interpreting them challenging. This phenomenon, known as superposition, has spurred efforts to find architectures that are more interpretable than standard…

Machine Learning · Computer Science 2023-05-08 Lee Sharkey

We propose an auto-encoder architecture for multi-texture synthesis. The approach relies on both a compact encoder accounting for second order neural statistics and a generator incorporating adaptive periodic content. Images are embedded in…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Pierrick Chatillon , Yann Gousseau , Sidonie Lefebvre

An additive autoencoder for dimension reduction, which is composed of a serially performed bias estimation, linear trend estimation, and nonlinear residual estimation, is proposed and analyzed. Computational experiments confirm that an…

Machine Learning · Computer Science 2022-10-14 Tommi Kärkkäinen , Jan Hänninen

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Machine Learning · Computer Science 2020-07-08 Tianxiao Shen , Jonas Mueller , Regina Barzilay , Tommi Jaakkola

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Physics-constrained data-driven computing is an emerging computational paradigm that allows simulation of complex materials directly based on material database and bypass the classical constitutive model construction. However, it remains…

Numerical Analysis · Mathematics 2022-09-12 Xiaolong He , Qizhi He , Jiun-Shyan Chen

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that…

Machine Learning · Statistics 2018-04-04 Christoph Wehmeyer , Frank Noé

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold. Our such-generated neural networks, called Flattening…

Machine Learning · Computer Science 2023-09-11 Michael Psenka , Druv Pai , Vishal Raman , Shankar Sastry , Yi Ma

Given data, deep generative models, such as variational autoencoders (VAE) and generative adversarial networks (GAN), train a lower dimensional latent representation of the data space. The linear Euclidean geometry of data space pulls back…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Line Kuhnel , Tom Fletcher , Sarang Joshi , Stefan Sommer

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

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Computation and Language · Computer Science 2021-09-14 Ivan Montero , Nikolaos Pappas , Noah A. Smith

Representation of data on mixed variables, numerical and categorical types to get suitable feature map is a challenging task as important information lies in a complex non-linear manifold. The feature transformation should be able to…

Machine Learning · Computer Science 2020-09-22 Saswata Sahoo , Souradip Chakraborty

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Tristan Aumentado-Armstrong , Stavros Tsogkas , Allan Jepson , Sven Dickinson

In many machine learning tasks, learning a good representation of the data can be the key to building a well-performant solution. This is because most learning algorithms operate with the features in order to find models for the data. For…

Machine Learning · Computer Science 2020-05-22 David Charte , Francisco Charte , María J. del Jesus , Francisco Herrera

Wide accessibility of imaging and profile sensors in modern industrial systems created an abundance of high-dimensional sensing variables. This led to a a growing interest in the research of high-dimensional process monitoring. However,…

Machine Learning · Computer Science 2022-08-15 Nurettin Sergin , Hao Yan

Enhanced modeling of microlensing variations in light curves of strongly lensed quasars improves measurements of cosmological time delays, the Hubble Constant, and quasar structure. Traditional methods for modeling extra-galactic…

Instrumentation and Methods for Astrophysics · Physics 2025-01-03 Somayeh Khakpash , Federica Bianco , Georgios Vernardos , Gregory Dobler , Charles Keeton
‹ Prev 1 3 4 5 6 7 10 Next ›