Programmatic Policy Extraction by Iterative Local Search

Autor: Larsen, Rasmus, Schmidt, Mikkel Nørgaard

Reinforcement learning policies are often represented by neural networks, but programmatic policies are preferred in some cases because they are more interpretable, amenable to formal verification, or generalize better. While efficient algorithms for

Externí odkaz: http://arxiv.org/abs/2201.06863

Single-channel source separation using non-negative matrix factorization

Autor: Schmidt, Mikkel Nørgaard

Publikováno v: Schmidt, M N 2009, Single-channel source separation using non-negative matrix factorization . IMM-PHD-2008-205, Technical University of Denmark, DTU Informatics, Building 321, Kgs. Lyngby .

Single-channel source separation problems occur when a number of sources emit signals that are mixed and recorded by a single sensor, and we are interested in estimating the original source signals based on the recorded mixture. This problem, which o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1202::9af99b4857ff67936da409222e2e31ed
https://orbit.dtu.dk/en/publications/226c9882-21b7-4118-9334-52ff3a08f23d