Adjoint operators enable fast and amortized machine learning based Bayesian uncertainty quantification

Keyphrases

• Machine Learning Based 100%
• Photoacoustic Imaging 100%
• Bayesian Uncertainty Quantification 100%
• Adjoint Operator 100%
• Computed Tomography 66%
• Medical Imaging 66%
• Inverse Problem 66%
• Challenging Tasks 33%
• Uncertainty Quantification 33%
• Imaging Tomography 33%
• Forward Operator 33%
• Neural Network 33%
• Fast Convergence 33%
• Point Estimate 33%
• Preprocessing Techniques 33%
• Quantification Method 33%
• Time Reversal 33%
• Acoustic Data 33%
• Back-projection 33%
• Bayesian Inference Method 33%
• Posterior Inference 33%
• Machine Learning Algorithms 33%
• Computer Tomography Imaging 33%
• Unknown Model 33%
• Receiver Type 33%
• Receiver Configuration 33%
• SSIM Index 33%

Computer Science

• Adjoint Operator 100%
• Machine Learning 100%
• Learning System 100%
• Computer Assisted Tomography 100%
• Inverse Problem 66%
• Medical Imaging 66%
• Neural Network 33%
• Fast Convergence 33%
• Machine Learning Algorithm 33%
• Backprojection 33%
• Preprocessing Technique 33%
• Point Estimate 33%
• Inference Method 33%

Mathematics

• Bayesian 100%
• Adjoint Operator 100%
• Adjoints 100%
• Uncertainty Quantification 100%
• Bayesian Inference 16%
• Inference Method 16%
• Observed Data 16%
• Neural Network 16%
• Point Estimate 16%