Implementation of Deep Neural Networks for Industry Applications
Paweł Różycki, Janusz Kolbusz, Grzegorz Krzos, Bogdan M. Wilamowski · 2018
Deep learning become a popular trend in current research and applications. Deep neural networks are important part of this trend. The paper shows the effect of neural network architecture on its power and capacity for solving complex, nonlinear problems. The problem has been analyzed using trigonometric, polynomial and digital approaches. Presented analysis show that the network capacity increases linearly with the network width and increases exponentially with the network depth.