Abstract: Devices, systems, kits, software and methods for using deep learning for enhanced identification of anatomical structures or tissue types during eye surgery.

Abstract: The invention relates to a modular, mobile, compact, multi-stage and highly efficient biogas facility, a method for operating a modular biogas facility, and a system for the computer-assisted, decentralized monitoring and control of at least one modular biogas facility. The system can be equipped with modular, local intelligence and a local control unit. The modular biogas facility is provided with a plurality of tanks for accommodating biomass. The tanks can be fluidically connected to one another. Furthermore, at least one gas reservoir is provided for the biogas produced in the modular biogas facility. Each of the tanks is a module in the biogas facility. Each tank can be positioned in a rigid and cuboidal frame, with the cuboidal frame having six side faces. The side faces of the cuboidal frame define an envelope for the tank.

Abstract: Multiple machine learning models can be jointly trained in parallel. An example process for jointly training multiple machine learning models includes providing a set of machine learning models that are to learn a respective task, the set of machine learning models including a first machine learning model and a second machine learning model. The process can initiate training of the first machine learning model to learn a task using training data. During the training of the first machine learning model, information can be passed between the first machine learning model and the second machine learning model. Such passing of information (or “transfer of knowledge”) between the machine learning models can be accomplished via the formulation, and optimization, of an objective function that comprises model parameters that are based on the multiple machine learning models in the set.