Autonomous Learning of Representations

Abstract

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.

Combined multiscale segmentation convolutional neural network for rapid damage mapping from postearthquake very high-resolution images

“…The entire system of CNN is trained end to end, from raw pixels to ultimate categories, thereby alleviating the requirement to manually design a suitable feature extractor. 23,24 This enables CNN to be widely utilized in hyperspectral image classification. [25][26][27] However, in spite of the remarkable achievement in the application of hyperspectral images, there still exist recurring limitations when applied in the feature extraction of high-resolution images.…”