Abstract: Provided is a hydrocracking process with a recycle loop for converting a petroleum feed to lower boiling products, which process comprises reacting a stream over a non-zeolite noble metal catalyst at a temperature of about 650° F. (343° C.) or less in a reactor positioned in the recycle loop of the hydrocracking reactor.

Abstract: A privacy-preserving DNN model compression framework allows a system designer to implement a pruning scheme on a pre-trained model without the access to the client's confidential dataset. Weight pruning of the DNN model is formulated without the original dataset as two sets of optimization problems with respect to pruning the whole model or each layer are solved successfully with an ADMM optimization framework. The system allows data privacy to be preserved and real-time inference to be achieved while maintaining accuracy on large-scale DNNs.