학술논문
Estimation of deep neural networks capabilities based on a trigonometric approach
Document Type
Conference
Author
Source
2016 IEEE 20th Jubilee International Conference on Intelligent Engineering Systems (INES) Intelligent Engineering Systems (INES), 2016 IEEE 20th Jubilee International Conference on. :303-308 Jun, 2016
Subject
Language
Abstract
The rapid development of computing machines led to renewed interest in deep neural networks. For years it is known that they have a great possibilities, but to use them new training algorithms are required. The paper shows benefits for deep neural networks usage by analysis of the Fourier series approximation of the activation function for shallow and deep neural network architectures. The proposed approach has been confirmed by experiments.