Uncertainty-aware deep learning for reliable health monitoring in safety-critical energy systems
In recent years, significant advancements in deep learning technology have facilitated the
development of intelligent health monitoring approaches for energy systems. However …
development of intelligent health monitoring approaches for energy systems. However …
Trustworthy Bayesian deep learning framework for uncertainty quantification and confidence calibration: Application in machinery fault diagnosis
Reliable and accurate machinery fault diagnosis is crucial for ensuring operational safety
and reducing downtime in industrial settings. Traditional intelligent diagnosis methods only …
and reducing downtime in industrial settings. Traditional intelligent diagnosis methods only …
Marginalization is not marginal: No bad vae local minima when learning optimal sparse representations
D Wipf - International Conference on Machine Learning, 2023 - proceedings.mlr.press
Although the variational autoencoder (VAE) represents a widely-used deep generative
model, the underlying energy function when applied to continuous data remains poorly …
model, the underlying energy function when applied to continuous data remains poorly …
Learning sparse codes with entropy-based elbos
Standard probabilistic sparse coding assumes a Laplace prior, a linear mapping from latents
to observables, and Gaussian observable distributions. We here derive a solely entropy …
to observables, and Gaussian observable distributions. We here derive a solely entropy …
Theoretical Convergence Guarantees for Variational Autoencoders
S Surendran, A Godichon-Baggioni, SL Corff - arXiv preprint arXiv …, 2024 - arxiv.org
Variational Autoencoders (VAE) are popular generative models used to sample from
complex data distributions. Despite their empirical success in various machine learning …
complex data distributions. Despite their empirical success in various machine learning …
On the Convergence of the ELBO to Entropy Sums
J Lücke, J Warnken - arXiv preprint arXiv:2209.03077, 2022 - arxiv.org
The variational lower bound (aka ELBO or free energy) is the central objective for many
established as well as many novel algorithms for unsupervised learning. During learning …
established as well as many novel algorithms for unsupervised learning. During learning …
Learning Deep Generative Models Based on Binomial Log-Likelihood
Y Kim, I Kong, H Jeong - Available at SSRN 5016722 - papers.ssrn.com
Likelihood-based learning algorithms for deep generative models mostly use the Gaussian
loglikelihood. One of the exceptions is the binomial log-likelihood in the Wasserstein …
loglikelihood. One of the exceptions is the binomial log-likelihood in the Wasserstein …