On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Cycle-GAN”

Anomaly Generation using Generative Adversarial Networks in Host Based Intrusion Detectioncs.LG

Generative adversarial networks generate synthetic anomalies for host-based intrusion detection.

problem Imbalanced datasets in host-based intrusion detection.

method Cycle-GAN to generate synthetic anomalies from normal data.

result Improved anomaly detection with higher AUC and anomaly detection rate.

Generative Adversarial Networks Intrusion Detection Anomaly Generation Cycle-GAN Imbalanced Data

2018-12-11abs ↗pdf ↗

Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoisingeess.IV

New CycleGAN uses invertible generator for faster, less resource-intensive CT denoising.

problem Efficient unsupervised CT denoising without paired data.

method Single generator with wavelet residual domain, no discriminators, cycle consistency via invertible generator.

result Significantly improved denoising performance with faster training and less parameters.

CycleGAN CT Denoising Invertible Generator Wavelets Low-Dose Imaging

2021-04-17abs ↗pdf ↗

Adversarial training approach for local data debiasingcs.LG

GANsan removes sensitive attributes from data to prevent discrimination.

problem Preventing discrimination in automated decision processes.

method Generative adversarial networks (GANs) to modify attributes without losing interpretability.

result Demonstrated effectiveness and trade-off between fairness and utility on real data.

discrimination automated decision fairness GANs data sanitization

2019-06-19abs ↗pdf ↗

Recent Developments Combining Ensemble Smoother and Deep Generative Networks for Facies History Matchingcs.LG

Combining deep learning and ensemble smoothers for better history matching.

problem Dealing with complex facies distributions in history matching.

method Using autoencoders and generative adversarial networks to parameterize facies models, applying distance-based localization.

result Improved history matching performance with deep learning parameterizations.

ensemble smoother deep learning history matching facies modeling autoencoder

2020-05-08abs ↗pdf ↗