Machine learning application benchmarking on COTS inference processors

Abstract

The objective of the MaLeBeCo project is to build a test-bed allowing the comparison and benchmarking of machine learning applications for low-, midand high-performance architectures. This is of particular interest, in order to be able to cover the wide application area which is given by the different mission scenarios and use-cases. These use-cases include among other: the provision of pre-processed smart payload data, guidance navigation and control (GNC) for satellites as well as robots, onboard AI for an increased level of autonomy, intelligent data exploration algorithms, as well as AI in operations on ground or in orbit.