REVIEW 10 cited by
Autoencoders
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
An autoencoder is a specific type of a neural network, which is mainly designed to encode the input into a compressed and meaningful representation, and then decode it back such that the reconstructed input is similar as possible to the original one. This chapter surveys the different types of autoencoders that are mainly used today. It also describes various applications and use-cases of autoencoders.
Forward citations
Cited by 10 Pith papers
-
What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?
DP-SGD causes large utility loss in deep trajectory generation, a new DP mechanism for conditional inputs helps stabilize GANs, and GANs overtake diffusion models when formal privacy is required.
-
Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R
Per-layer late fusion of one-class softmax classifiers on frozen XLS-R features achieves 6.90% EER on In-the-Wild fake-audio detection, outperforming feature-fusion and single-layer baselines.
-
BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks
An active-inference xApp with a hand-coded generative model outperforms DRL baselines on dynamic radio resource slicing and provides belief-based explanations of its decisions.
-
The contribution of the color space in LSST-like photometry for the selection of extragalactic globular cluster candidates
With ugrizY colors alone, an LSST-like catalog yields at best ~35% contamination and ~19% completeness for globular-cluster candidates; principal components help marginally, autoencoders do not.
-
NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detection
A multi-task self-supervised method combining contrastive, reconstruction and classification losses with learnable transformations, evaluated on UCR time series anomaly detection problems.
-
A Wavelength-Aware Unsupervised Learning Approach for Large, Multicolor, Photometric Surveys
An LSTM autoencoder encodes Pan-STARRS grizy photometry into a 2D latent space that reconstructs 99.51% of stars within 0.05 mag and flags outliers through reconstruction error.
-
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
SafetyNet is an ensemble of standard outlier detectors for LLM backdoor monitoring, but its key mechanistic claim and headline numbers are contradicted by inconsistent tables and a mismatched abstract.
-
OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
Autoencoders as continuous-time optimal control problems solved with rank-adaptive tensor compression, yielding memory savings and automatic layer-width profiles on MNIST denoising and deblurring.
-
Completion of the DrugMatrix Toxicogenomics Database using 3-Dimensional Tensors
A tensor-completion model with attention and a weighted loss is reported to fill missing DrugMatrix gene-expression values more accurately than 2D matrix factorization and CP decomposition.
-
Machine Learning Based Stress Testing Framework for Indian Financial Market Portfolios
The paper applies PCA, autoencoder, and variational autoencoder pipelines to Indian sector portfolios and reports elevated tail risk during historical crises, though the VAE sampling does not actually produce stressed...
Discussion (0). Continue with ORCID to comment.