HRL Laboratories, LLC, has launched an ambitious project to develop a machine learning system that leverages knowledge of a set of labeled data onto a new unlabeled data set the way a child can recognize a zebra while only having ever seen a horse, but being told that zebras look like striped horses.
Scientists at HRL Laboratories have published their new framework for training computer deep neural networks to be able to classify synthetic aperture radar (SAR) images without a large labeled data set, solving the problem of SAR image identification when only a few labeled data were available.
HRL Laboratories, LLC, joins DARPA’s Lifelong Learning Machines (L2M) program to develop a breakthrough in machine-learning architectures for autonomous systems that will continually improve performance and update their knowledge based on experience, without human supervision.