Context-Aware Learning for Generative Models

This work studies the class of algorithms for learning with side-information that emerges by extending generative models with embedded context-related variables. Using finite mixture models (FMMs) as the prototypical Bayesian network, we show that maximum-likelihood estimation (MLE) of parameters th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transaction on neural networks and learning systems Jg. 32; H. 8; S. 3471 - 3483
Hauptverfasser: Perdikis, Serafeim, Leeb, Robert, Chavarriaga, Ricardo, Millan, Jose del R.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.08.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Approximation algorithms
Artificial neural networks
Bayesian analysis
Brain-computer interfaces
Classification
Context
Context awareness
Context modeling
Deep learning
expectation–maximization (EM)
Extremities
finite mixture models (FMMs)
Learning systems
Machine learning
Mathematical models
maximum likelihood (ML)
Maximum likelihood estimation
Neural networks
Parameter estimation
Probabilistic logic
Probabilistic models
side information
unsupervised learning
variational autoencoder (VA)
ISSN:2162-237X, 2162-2388, 2162-2388
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This work studies the class of algorithms for learning with side-information that emerges by extending generative models with embedded context-related variables. Using finite mixture models (FMMs) as the prototypical Bayesian network, we show that maximum-likelihood estimation (MLE) of parameters through expectation-maximization (EM) improves over the regular unsupervised case and can approach the performances of supervised learning, despite the absence of any explicit ground-truth data labeling. By direct application of the missing information principle (MIP), the algorithms' performances are proven to range between the conventional supervised and unsupervised MLE extremities proportionally to the information content of the contextual assistance provided. The acquired benefits regard higher estimation precision, smaller standard errors, faster convergence rates, and improved classification accuracy or regression fitness shown in various scenarios while also highlighting important properties and differences among the outlined situations. Applicability is showcased with three real-world unsupervised classification scenarios employing Gaussian mixture models. Importantly, we exemplify the natural extension of this methodology to any type of generative model by deriving an equivalent context-aware algorithm for variational autoencoders (VAs), thus broadening the spectrum of applicability to unsupervised deep learning with artificial neural networks. The latter is contrasted with a neural-symbolic algorithm exploiting side information.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2020.3011671