TY - JOUR AB - Besides the core learning algorithm itself, one major question in machine learning is how to best encode given training data such that the learning technology can efficiently learn based thereon and generalize to novel data. While classical approaches often rely on a hand coded data representation, the topic of autonomous representation or feature learning plays a major role in modern learning architectures. The goal of this contribution is to give an overview about different principles of autonomous feature learning, and to exemplify two principles based on two recent examples: autonomous metric learning for sequences, and autonomous learning of a deep representation for spoken language, respectively. AU - Walter, Oliver AU - Haeb-Umbach, Reinhold AU - Mokbel, Bassam AU - Paassen, Benjamin AU - Hammer, Barbara ID - 11922 JF - KI - Kuenstliche Intelligenz KW - Representation learning KW - Metric learning KW - Deep representation KW - Spoken language TI - Autonomous Learning of Representations ER -