Dedicated deep neural network architectures and methods for their training
Paweł Różycki, Janusz Kolbusz, Bogdan M. Wilamowski · 2015
Deep neural networks are currently very popular trend in artificial intelligence. While such networks are very powerful they are difficult in training. The paper discusses capabilities of different neural network architectures and presents the proposition of new multilayer architecture with additional connections across layers, called Bridged MLP, that is much easier to train that traditional MLP network. Efficiency of suggested approach has been confirmed by several experiments.