Document Type


Publication Date



The fields of computer vision and image processing from their initial days have been dealing with the problems of visual recognition. Convolutional Neural Networks (CNNs) in machine learning are deep architectures built as feed-forward neural networks or perceptrons, which are inspired by the research done in the fields of visual analysis by the visual cortex of mammals like cats. This work gives a detailed analysis of CNNs for the computer vision tasks, natural language processing, fundamental sciences and engineering problems along with other miscellaneous tasks. The general CNN structure along with its mathematical intuition and working, a brief critical commentary on the advantages and disadvantages, which leads researchers to search for alternatives to CNN’s are also mentioned. The paper also serves as an appreciation of the brain-child of past researchers for the existence of such a fecund architecture for handling multidimensional data and approaches to improve their performance further.