Data Science and Machine Learning: The Weaker the Better
Wednesday, October 28, 2020
11:00 am - 12:00 pm
About the Event:
Seismic interpretation is a problem with lots of data but few annotations/labels. The ground-truth location of salt structures or facies is available from borehole measurements. These are very expensive and sparsely available. Workflows often include manually labeling many seismic images for training. In this case, a neural network trains to mimic the human interpreter, not to achieve the best possible accuracy. This approach is also time-intensive, and we would like to avoid manual labeling.
We propose a problem formulation that does require not any annotated/labeled seismic images. Instead, weak information about the targets/horizons/facies of interest is sufficient for training. Weak supervision may include arbitrarily shaped points/lines/shapes that only annotate what is not interesting. In both cases, the weak supervision encodes information about the minimum and maximum bounds on the expected ‘size’ or ‘surface area’ of the object that we want to segment.
The application of such ideas has been problematic due to the computationally expensive alternating optimization procedures that result from many formulations for training using weak supervision networks. We propose a new formulation based on point-to-set distance functions, where constraint sets on the output of a neural network encode the weak information. An examination of the Lagrangian structure of the problem reveals a way to merge our approach into standard backpropagation based training seamlessly. We demonstrate that we can segment salt structures and layers on two different datasets without having any annotation of those targets.
Professor Bas Peters is interested in convex and nonconvex constrained optimization, image processing and the connection to inverse problems. He is an expert in neural-networks and computer vision from the inverse problem point of view. He also works in numerical linear algebra, particularly solvers for (block-) structured least-squares problems. Some of his favorite applications are geoscience problems.