One flexible model for multiclass gravitational wave signal and glitch generation

Keyphrases

• Synthetic Data 100%
• Gravitational Waves 100%
• Glitch 100%
• Multi-class 100%
• Flexible Model 100%
• Convolutional Neural Network 75%
• Three-class 50%
• Area under the Curve 50%
• Glitches 50%
• Binary Black Holes 50%
• Hybrid Sample 50%
• GAN Model 50%
• Data Challenge 25%
• Network Framework 25%
• Generated Data 25%
• Data Augmentation 25%
• Generative Adversarial Networks 25%
• Transient Noise 25%
• Gravitational Wave Detectors 25%
• Real Samples 25%
• Curving Performance 25%
• Multiple Classes 25%
• First Order Derivative 25%
• Balanced Dataset 25%
• Class Vector 25%
• Detector Background 25%
• Gravitational Wave Data Analysis 25%
• Noise Bursts 25%
• Detector Noise 25%
• Convolutional Neural Network Architecture 25%
• LIGO Detectors 25%
• Gravitational Radiation Detectors 25%
• Semi-analytical Model 25%
• Blip 25%
• Fit Factor 25%
• Signal-to-noise Ratio 25%
• Adversarial Games 25%
• Training Symbol 25%
• Detection Scheme 25%
• Parameter Space 25%
• Events of Interest 25%
• Signal Search 25%
• Data Analysis Tasks 25%
• Synthetic Signals 25%
• Conditional Model 25%
• Black Hole Mergers 25%
• Factor Study 25%
• Machine Learning Applications 25%
• Augmentation Approach 25%

Computer Science

• Convolutional Neural Network 100%
• Synthetic Data 50%
• Synthetic Datasets 50%
• Black Holes 50%
• Simulated Data 25%
• Data Augmentation 25%
• Neural Network Architecture 25%
• Discriminator 25%
• Generative Adversarial Networks 25%
• Noise-to-Signal Ratio 25%
• Downstream Data 25%
• Training Signal 25%
• Parameter Space 25%
• Machine Learning 25%
• Learning System 25%

Engineering

• Convolutional Neural Network 100%
• Time Domain 75%
• Illustrates 25%
• Transients 25%
• Discriminator 25%
• Real Sample 25%
• Neural Network Architecture 25%
• Signal-to-Noise Ratio 25%
• Parameter Space 25%
• Detection Scheme 25%
• Performance Curve 25%
• Simulated Data 25%
• Learning System 25%