arrow
返回

Context-Aware Learning for Generative Models

delete2021-08-01
delete4
delete
OA
AI
S
Serafeim Perdikis *
R
Robert Leeb
R
Ricardo Chavarriaga
J
José del R. Millán
DOI:10.1109/TNNLS.2020.3011671delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
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.
Keyword:
Context modeling
Maximum likelihood estimation
Brain-computer interfaces
Learning systems
Probabilistic logic
Approximation algorithms
Context awareness
expectation-maximization (EM)
finite mixture models (FMMs)
maximum likelihood (ML)
parameter estimation
side information
unsupervised learning
variational autoencoder (VA)
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Neural Networks and Learning Systems 封面图
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
论文数:
7.8K
被引数:
9.0W

机构

S
swiss federal institutes of technology domain
学者数:
795
论文数: 1.1K
被引数: 9.3W
引用论文

引用论文

Dendritic-cell vaccines on the move
err2015-03-11
err0
errOAAI
errRachel Lubong Sabado; Nina Bhardwaj
err分享
err收藏
PhIP-Seq Reveals Autoantibodies for Ubiquitously Expressed Antigens in Viral Myocarditis
err2022-07-13
err0
errOAAI
errMahima T. Rasquinha; Ninaad Lasrado; Erika Petro-Turnquist; Eric Weaver; Thiagarajan Venkataraman; Daniel Anderson; Uri Laserson; H. Benjamin Larman; Jay Reddy
err分享
err收藏
Clinical evaluation of BrainTree, a motor imagery hybrid BCI speller
err2014-04-16
err68
errOAAI
errPerdikis, S.; Leeb, R.; Williamson, J.; Ramsay, A.; Tavella, M.; Desideri, L.; Hoogerwerf, E-J; Al-Khodairy, A.; Murray-Smith, R.; Millan, J. D. R.
err分享
err收藏
err分享
err收藏
ENSO signals in East African rainfall seasons
err2000-01-01
err0
PREAI
errMatayo Indeje; Fredrick H.M. Semazzi; Laban J. Ogallo
err分享
err收藏
err分享
err收藏
学者 查看更多内容