We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semiautomate t...
: Tuning numerical libraries has become more difficult over time, as systems get more sophisticated. In particular, modern multicore machines make the behaviour of algorithms hard ...
Emmanuel Agullo, Jack Dongarra, Rajib Nath, Stanim...
The family of natural evolution strategies (NES) offers a principled approach to real-valued evolutionary optimization by following the natural gradient of the expected fitness....
Tobias Glasmachers, Tom Schaul, Yi Sun, Daan Wiers...
We propose a theoretical framework for specification and analysis of a class of learning problems that arise in open-ended environments that contain multiple, distributed, dynamic...
—We propose novel discrete cosine transform (DCT) pseudophase techniques to estimate shift/delay between two onedimensional (1-D) signals directly from their DCT coefficients by...