Phenomenology-informed techniques for machine learning with measured and synthetic SAR imagery
Abstract not provided.
Publications
Phenomenology-informed techniques for machine learning with measured and synthetic SAR imagery
Proceedings of SPIE - The International Society for Optical Engineering
Phenomenology-Informed (PI) Machine Learning is introduced to address the unique challenges faced when applying modern machine-learning object recognition techniques to the SAR domain. PI-ML includes a collection of data normalization and augmentation techniques inspired by successful SAR ATR algorithms designed to bridge the gap between simulated and real-world SAR data for use in training Convolutional Neural Networks (CNNs) that perform well in the low-noise, feature-dense space of camera-based imagery. The efficacy of PI-ML will be evaluated using ResNet, EfficientNet, and other networks, using both traditional training techniques and all-SAR transfer learning.
Comparing Circuit Connectivity Between All-Metal GDS Layouts
Abstract not provided.
Comparing Circuit Connectivity Between All-Metal GDS Layouts
Abstract not provided.
Self-Tuning Seismic Sensor Data Processing
Abstract not provided.
5 Results