Open Access. Powered by Scholars. Published by Universities.®
- Publication Type
Articles 1 - 2 of 2
Full-Text Articles in Mathematics
When Is Deep Learning Better And When Is Shallow Learning Better: Qualitative Analysis, Salvador Robles Herrera, Martine Ceberio, Vladik Kreinovich
When Is Deep Learning Better And When Is Shallow Learning Better: Qualitative Analysis, Salvador Robles Herrera, Martine Ceberio, Vladik Kreinovich
Departmental Technical Reports (CS)
In many practical situations, deep neural networks work better than the traditional "shallow" ones, however, in some cases, the shallow neural networks lead to better results. At present, deciding which type of neural networks will work better is mostly done by trial and error. It is therefore desirable to come up with some criterion of when deep learning is better and when shallow is better. In this paper, we argue that this depends on whether the corresponding situation has natural symmetries: if it does, we expect deep learning to work better, otherwise we expect shallow learning to be more effective. …
Machine Learning Analysis To Characterize Phase Variations In Laser Propagation Through Deep Turbulence, Luis Fernando Rodriguez Sanchez
Machine Learning Analysis To Characterize Phase Variations In Laser Propagation Through Deep Turbulence, Luis Fernando Rodriguez Sanchez
Open Access Theses & Dissertations
The present Dissertation is focused on the analysis of the atmospheric conditions of a turbulent environmental system and its effects on the diffraction of a laser beam that moves through it. The study is based on the optical communication of two labs placed at the summit of two mountains located in Maui, Hawaii. The emitter system is located at the Mauna Loa mountain and the receiver at the Haleakala. The distance between both mountains is 150 km. The emitter system is at a height of 3.1 km and the receiver at 3.4 km. The maritime environment at the location experiences …