Autoencoders, Unsupervised Learning, and Deep Architectures

By Pierre Baldi. 2011

1,737 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Model Architectures

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “This kind of neural networks has been used mainly for solving unsupervised learning problems as well as transfer learning [42].”
Deep learning in neural networks: An overview (2014, background): “nonlinear AEs suffer from certain limitations (Baldi, 2012).”
A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “2) [44, 45] are mostly adopted for educational uses, as McCulloch and Pitts [1] cells are still used in this context.”
Unsupervised state representation learning with robotic priors: a robustness benchmark (2017, methodology): “For autoencoders [23], we used the same network as the priors for the encoding part, the same inner dimension as the priors (3) and 5 deconvolutional layers for decoding.”
Wasserstein Introspective Neural Networks (2017, background): “, the Boltzmann machine [17] or autoencoder [4, 24] architectures.”
Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder (2016, methodology): “Based on the principles of Autoencoder [14, 15], the target of the output sequence y = (y1, y2, .”
Neural Ranking Models with Weak Supervision (2017, background): “Other generative approaches such as language modeling in NLP, and, more recently, various avors of auto-encoders [2] and generative adversarial networks [13] in computer vision have shown a promise in building more accurate models.”
Ensemble deep learning in bioinformatics (2020, background): “In autoencoders 20 , networks are constructed with an encoder and a decoder that together learn a more efficient latent space representation of the original higher-dimensional data.”
Deep learning in medical image registration: a review (2019, background): “An autoencoder (AE) is a type of neural network that learns to copy its input to its output without supervision [7].”
Layer-wise training of deep networks using kernel similarity (2017, background): “Autoencoders play an important role in unsupervised learning for deep architectures.”
Autoencoding the retrieval relevance of medical images (2015, methodology): “The method processes pixel position, intensity, probability of intensity and distance.”
Boolean autoencoders and hypercube clustering complexity (2012, background): “From the study of different kinds of autoencoders [4,2] emerge a set of basic properties that ought to be investigated for each class of autoencoders.”
Machine Learning: Algorithms, Real-World Applications and Research Directions (2021, methodology): “The autoencoder (AE) [15] is another learning technique that is widely used for dimensionality reduction as well and feature extraction in unsupervised learning tasks.”
Introspective Classification with Convolutional Nets (2017, methodology): “Other generative modeling schemes such as MiniMax entropy [50], inducing features [6], auto-encoder [1], and recent CNN-based generative modeling approaches [48, 47] are not for discriminative classification and they do not have a single model that is both generative and discriminative.”
Convergence Guarantees for RMSProp and ADAM in Non-Convex Optimization and an Empirical Comparison to Nesterov Acceleration (2018, methodology): “The loss function, for an input z is then given by: f Such autoencoders are a fairly standard setup that have been used in previous work [2, 5, 22, 41].”
State-of-the-art review on deep learning in medical imaging. (2019, methodology): “Autoencoder neural network (37) like DBN is an unsupervised learning algorithm applying backpropagation for learning.”
TabNet: Attentive Interpretable Tabular Learning (2019, background): “We explore the capability of TabNet in learning semantically-meaningful representations by integrating it into an autoencoder framework (Baldi, 2012).”