Search
Now showing items 1-2 of 2
Applied High-Order Singular Value Decomposition for Weight Compression and Expansion in Deep Neural Networks
(2019-08)
Complex deep learning objectives such as object detection and saliency, semantic segmentation, sequence-to-sequence translation, and others have given rise to training processes requiring increasing amounts of time and ...
Nurturing as Safe Exploration Promotes the Evolution of Generalized Supervised Learning
(2017-08-01)
The ability to learn is often a desirable property of intelligent systems which can make them more adaptive. However, it is difficult to develop sophisticated learning algorithms that are effective. One approach to the ...