Despite the advancements in deep learning and automated feature extraction techniques, the manual process of feature engineering remains a critical step for many models, especially in scenarios ...

One of the promises of deep learning is replacing handcrafted features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction. In this ...

Xiao Xu, Yunfei Yang, Tuanhui Zhou, Song Feng, Bo Liang, Wei Dai, Xianyong Bai, Sunspots Extraction in PMO Sunspot Drawings Based on Deep Learning, Publications of the Astronomical Society of the ...

We introduce unFEAR, Unsupervised Feature Extraction Clustering, to identify economic crisis regimes. Given labeled crisis and non-crisis episodes and the corresponding features values, unFEAR uses ...