no code implementations • ICON 2020 • Dong-Ho Jeong, Min-Kang Heo, Hyung-Chul Kim, Sang-Won Park
Data of 8, 043 sentences were constructed using the proposed method, and the performance of the named entity recognizer reached 80. 84%.
no code implementations • 15 Aug 2020 • Stephen Whitelam, Viktor Selin, Sang-Won Park, Isaac Tamblyn
We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise.