A Survey on Convolution Neural Networks

Abstract

Major tools to implement any Artificial Intelligence and Machine Learning systems are Symbolic AI and Artificial Neural Network (ANN) AI. ANN has made a dramatic improvement in the versatile area of Machine Learning (ML). ANN is a gathering of vast number of weighted interconnected artificial neurons, initially invented with the inspiration of biological neurons. These models are much better than previous models implemented with Symbolic AI so far as their performance is concerned. One revolutionary change in ANN is Convolution Neural Network (CNN). These structures are mainly suitable for complex pattern recognition tasks within images. Here we would discuss basics of ANN as a tool for complex pattern recognition and image processing task. Also some applications of the CNN tool we will present OCR based text translation and biometric based uni modal and multimodal person identification systems.