Applying the Standard Non-linearity of Cellular Neural Networks in Convolutional Networks

Abstract:
Cellular Neural Networks were used with success in the past decades and helped laying the foundations of neural network applications in image processing. In the last few years convolutional networks have appeared and helped in the solution of complex practical problems. There are many aspects, building blocks and elements in Cellular Networks which can be exploited in the field of modern machine learning.In this paper we show, how the application of the standard non-linearity of Cellular Neural Networks can increase the training speed and accuracy of Convolutional Neural Networks.