Abstract: Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.

Abstract: A drilling assembly for downhole to surface communications is provided. The drilling assembly includes a series of pipe segments coupled in fluid communication between a slip ring assembly and an end pipe portion. The slip ring assembly is coupled in data and fluid communication with the pipe segments. A surface communications link is in data communication with the drilling assembly via the slip ring assembly. An end pipe portion is coupled with the drilling assembly that includes an electronics assembly with electronic components for transferring data to the slip ring assembly via the drilling assembly. A drill bit is operably coupled with the end pipe portion for drilling a borehole. Each pipe segment includes an outer conductor portion, a hollow inner conductor portion, and a dielectric portion for electrical isolation between the outer conductor portion and the inner conductor portion.

Abstract: Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.