Data provided by National Institute of Standards and Technology
This research software package contains Python code to execute experiments on deep generative modeling of classical random process models for noise time series. Specifically, it includes Pytorch implementations of two generative adversarial network (GAN) models for time series based on convolutational neural networks (CNNs): WaveGAN, a 1-D CNN model, and STFT-GAN, a 2-D CNN model. In addition, there are methods for generating and evaluating noise time series defined several by classical random process models.
About this Dataset
Updated: 2024-02-22
Metadata Last Updated:
2022-07-03 00:00:00
Date Created:
N/A
Views:
Data Provided by:
time series
Dataset Owner:
N/A
| Title | Software for Evaluating Convolutional Generative Adversarial Networks with Classical Random Process Noise Models |
|---|---|
| Description | This research software package contains Python code to execute experiments on deep generative modeling of classical random process models for noise time series. Specifically, it includes Pytorch implementations of two generative adversarial network (GAN) models for time series based on convolutational neural networks (CNNs): WaveGAN, a 1-D CNN model, and STFT-GAN, a 2-D CNN model. In addition, there are methods for generating and evaluating noise time series defined several by classical random process models. |
| Modified | 2022-07-03 00:00:00 |
| Publisher Name | National Institute of Standards and Technology |
| Contact | mailto:[email protected] |
| Keywords | time series , machine learning , band-limited noise , power law noise , shot noise , impulsive noise , colored noise , fractional Gaussian noise , fractional Brownian motion |
{
"identifier": "ark:\/88434\/mds2-2695",
"accessLevel": "public",
"contactPoint": {
"hasEmail": "mailto:[email protected]",
"fn": "Adam Wunderlich"
},
"programCode": [
"006:045"
],
"@type": "dcat:Dataset",
"landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-2695",
"description": "This research software package contains Python code to execute experiments on deep generative modeling of classical random process models for noise time series. Specifically, it includes Pytorch implementations of two generative adversarial network (GAN) models for time series based on convolutational neural networks (CNNs): WaveGAN, a 1-D CNN model, and STFT-GAN, a 2-D CNN model. In addition, there are methods for generating and evaluating noise time series defined several by classical random process models.",
"language": [
"en"
],
"title": "Software for Evaluating Convolutional Generative Adversarial Networks with Classical Random Process Noise Models",
"distribution": [
{
"accessURL": "https:\/\/github.com\/usnistgov\/NoiseGAN",
"format": "python source code",
"description": "GitHub repository",
"title": "GitHub repository"
}
],
"license": "https:\/\/www.nist.gov\/open\/license",
"bureauCode": [
"006:55"
],
"modified": "2022-07-03 00:00:00",
"publisher": {
"@type": "org:Organization",
"name": "National Institute of Standards and Technology"
},
"theme": [
"Mathematics and Statistics:Image and signal processing",
"Mathematics and Statistics:Modeling and simulation research"
],
"issued": "2022-07-08",
"keyword": [
"time series",
"machine learning",
"band-limited noise",
"power law noise",
"shot noise",
"impulsive noise",
"colored noise",
"fractional Gaussian noise",
"fractional Brownian motion"
]
}
