Live briefing
Everything about Autoencoder
Neural network that learns efficient data encoding in an unsupervised manner
An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data. An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction, to generate lower-dimensional embeddings for subsequent use by other machine learning algorithms. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: AutoencoderA 5-minute orientation
- Skim a recent paper: Anomaly Detection Based on Convolutional Recurrent Autoencoder for IoT Time SeriesInfluential work since 2022
- Pick up a classic book: Advanced Deep Learning with KerasThe most-reprinted book on the subject
- Read the landmark paper: LLNet: A deep autoencoder approach to natural low-light image enhancementCited 1,898 times
- Go sideways: Variational autoencoderA closely related topic
- Go sideways: Unsupervised learningA closely related topic
📖 Definitions
Noun A form of neural network designed to learn codings.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
LLNet: A deep autoencoder approach to natural low-light image enhancement
A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder
Single-cell RNA-seq denoising using a deep count autoencoder
Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network
Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images
Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification
A novel deep autoencoder feature learning method for rotating machinery fault diagnosis
A comprehensive survey on design and application of autoencoder in deep learning
🆕 Influential since 2022
Anomaly Detection Based on Convolutional Recurrent Autoencoder for IoT Time Series
A comprehensive review of synthetic data generation in smart farming by using variational autoencoder and generative adversarial network
LSTM-Autoencoder-Based Anomaly Detection for Indoor Air Quality Time-Series Data
Context Autoencoder for Self-supervised Representation Learning
A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes
📚 Books worth reading
- 📕Advanced Deep Learning with KerasRowel Atienza · 2018
- 📕Quantum Generative Adversarial NetworksPethuru Raj, Amir Masoud Rahmani · 2025
Intelligent Science and Intelligent Data EngineeringJian Yang · 2013- 📕Dynamical Variational AutoencodersLaurent Girin, Simon Leglaive · 2021
- 📕Introduction to Variational AutoencodersDiederik P. Kingma, Max Welling · 2019
- 📕An Introduction to Variational AutoencodersDiederik P. Kingma, Max Welling · 2019
- 📕Potentialities of auto-encoding of scientific literatureH. P. Luhn · 1959
- 📕Auto-encoding of documents for information retrieval systemsH. P. Luhn · 1958
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Variational autoencoder In machine learning, a variational autoencoder (VAE) is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling in 2013…
- Unsupervised learning Unsupervised learning is a framework in machine learning where, in contrast to supervised learning, algorithms learn patterns exclusively from unlabeled…
- Neural field In machine learning, a neural field (also known as implicit neural representation, neural implicit, or coordinate-based neural network), is a mathematical…
- Representation learning In machine learning (ML), representation learning or feature learning is a set of techniques that allow a system to automatically discover the representations…
- Latent diffusion model The latent diffusion model (LDM) is a diffusion model architecture developed by the CompVis (Computer Vision & Learning) group at LMU Munich. Introduced…
- Activation function In artificial neural networks, the activation function of a node is a function that calculates the output of the node based on its individual inputs and…
- Vision transformer A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into…
- Batch normalization In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable…