Neural Network Autoencoder

Neural network autoencoders are deep learning models designed to learn efficient, compressed representations of data by encoding it into a lower-dimensional latent space and then reconstructing it. Current research focuses on improving reconstruction quality through techniques like incorporating diffusion models and adversarial losses, optimizing autoencoder architectures for specific data types (e.g., time series, images, spectrograms), and leveraging pre-trained models for improved performance and interpretability in downstream tasks. These advancements are impacting diverse fields, enabling improved anomaly detection in industrial systems, enhanced spectral unmixing in spectroscopy, and more efficient data visualization and classification in various applications.

Papers

September 4, 2024

Sample what you cant compress
Vighnesh Birodkar, Gabriel Barcik, James Lyon, Sergey Ioffe, David Minnen, Joshua V. Dillon
Supervised Autoencoder External Sample Autoencoder Model Generative Diffusion Neural Network Autoencoder

August 25, 2024

Improving Nonlinear Projection Heads using Pretrained Autoencoder Embeddings
Andreas Schliebitz, Heiko Tapken, Martin Atzmueller
Contrastive Learning Supervised Autoencoder Neural Network Autoencoder Pre Trained Embeddings Projection Head

May 23, 2024

Discretization of continuous input spaces in the hippocampal autoencoder
Adrian F. Amil, Ismael T. Freire, Paul F. M. J. Verschure
Data Discretization Neural Network Autoencoder Spatial Cognition Human Hippocampus Symbolic Memory Place Cell

May 14, 2024

Investigating the 'Autoencoder Behavior' in Speech Self-Supervised Models: a focus on HuBERT's Pretraining
Valentin Vielzeuf
Self Supervised Learning Speech Recognition Supervised Autoencoder Human Driving Focus Self Supervised Speech Model High Level Neural Network Autoencoder High Level Task

May 6, 2024

End-to-End Autoencoder for Drill String Acoustic Communications
Iurii Lezhenin, Aleksandr Sidnev, Vladimir Tsygan, Igor Malyshev
Autoencoder Model Neural Network Autoencoder

March 7, 2024

Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders
Dimitar Georgiev, Álvaro Fernández-Galiana, Simon Vilms Pedersen, Georgios Papadopoulos, Ruoxiao Xie, Molly M. Stevens, Mauricio Barahona
Supervised Autoencoder Neural Network Autoencoder Hyperspectral Unmixing Raman System Raman Spectroscopy

March 4, 2024

Towards efficient deep autoencoders for multivariate time series anomaly detection
Marcin Pietroń, Dominik Żurek, Kamil Faber, Roberto Corizzo
Deep Learning Multivariate Time Series Anomaly Detection Anomaly Detection Performance Neural Network Autoencoder Anomaly Detection Benchmark

February 14, 2024

Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio
Pablo Alonso-Jiménez, Leonardo Pepino, Roser Batlle-Roca, Pablo Zinemanas, Dmitry Bogdanov, Xavier Serra, Martín Rocamora
Supervised Autoencoder Pre Training Audio Classification Neural Network Autoencoder

January 17, 2024

Functional Autoencoder for Smoothing and Representation Learning
Sidi Wu, Cédric Beaulac, Jiguo Cao
Representation Learning Neural Network Autoencoder Functional Data Analysis Smoothing Factor Functional Principal Component Nonlinear Representation Functional Learning

January 4, 2024

SwitchTab: Switched Autoencoders Are Effective Tabular Learners
Jing Wu, Suiyao Chen, Qi Zhao, Renat Sergazinov, Chen Li, Shengjie Liu, Chongchao Zhao, Tianpei Xie, Hanqing Guo, Cheng Ji, Daniel Cociorva, Hakan Brunzel
Representation Learning Interpretable Representation Switch List Neural Network Autoencoder Tabular Learning Self Supervised Representation Learning Method

October 3, 2023

Why should autoencoders work?
Matthew D. Kvalheim, Eduardo D. Sontag
Supervised Autoencoder Intrinsic Dimension Neural Network Autoencoder Bottleneck Analysis Encoding Layer

September 12, 2023

Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection
Muhammad Sabbir Alam, Walid Al Misba, Jayasimha Atulasimha
Supervised Autoencoder Neural Network Autoencoder Magnetic Tunnel Junction Efficient Anomaly Detection Ferromagnetic Particle

August 31, 2023

Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders
Matthew B. Webster, Joonnyong Lee
Blind Source Separation Neural Network Autoencoder Single Channel Mixture

August 11, 2023

Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms
Kanishka Tyagi, Chinmay Rane, Michael Manry
Deep Learning Model Training Data Linear Classifier Efficient Deep Neural Network Autoencoder Second Order Algorithm

August 6, 2023

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning
Nikhil Ghosh, Spencer Frei, Wooseok Ha, Bin Yu
Stochastic Gradient Descent Stochastic Gradient Sparsity Increase Feature Learning Autoencoder Model Neural Network Autoencoder Node Feature Sharpness Full Batch Gradient Descent

April 19, 2023

Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images
Aleksandar A. Yanev, Galina D. Momcheva, Stoyan P. Pavlov
Classification Code Supervised Autoencoder Deep Learning Framework Efficient Optimization Microscopic Image Neural Network Autoencoder Latent Encoding Micro Level Situ Hybridization

March 17, 2023

Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness
Hao Liu, Alex Havrilla, Rongjie Lai, Wenjing Liao
Native Robustness Supervised Autoencoder Generalization Error Low Dimensional Manifold Autoencoder Based Neural Network Autoencoder Data Structure Classical Autoencoders Deep Nonparametric

March 12, 2023

Knowledge-integrated AutoEncoder Model
Teddy Lazebnik, Liron Simon-Keren
Data Encoding Autoencoder Model Neural Network Autoencoder Encoding Model

January 25, 2023

Deep Generative Neural Embeddings for High Dimensional Data Visualization
Halid Ziya Yerebakan, Gerardo Hermosillo Valadez
ImageNet Dataset Feature Embeddings Generative Network Image Embeddings Neural Network Autoencoder

January 18, 2023

An investigation of the reconstruction capacity of stacked convolutional autoencoders for log-mel-spectrograms
Anastasia Natsiou, Luca Longo, Sean O'Leary
Full State Reconstruction Comprehensive Investigation Time Frequency Convolutional Autoencoder Sound Synthesizer Neural Network Autoencoder Log Mel Spectrogram

Neural Network Autoencoder

Papers

Sample what you cant compress

Improving Nonlinear Projection Heads using Pretrained Autoencoder Embeddings

Discretization of continuous input spaces in the hippocampal autoencoder

Investigating the 'Autoencoder Behavior' in Speech Self-Supervised Models: a focus on HuBERT's Pretraining

End-to-End Autoencoder for Drill String Acoustic Communications

Hyperspectral unmixing for Raman spectroscopy via physics-constrained autoencoders

Towards efficient deep autoencoders for multivariate time series anomaly detection

Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio

Functional Autoencoder for Smoothing and Representation Learning

SwitchTab: Switched Autoencoders Are Effective Tabular Learners

Why should autoencoders work?

Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection

Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders

Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning

Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images

Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness

Knowledge-integrated AutoEncoder Model

Deep Generative Neural Embeddings for High Dimensional Data Visualization

An investigation of the reconstruction capacity of stacked convolutional autoencoders for log-mel-spectrograms