What is convolutional neural networks?
A convolutional neural networks is a class of deep neural networks and a type of artificial neural network. It is applied to analyze visual imagery; and it is designed to process pixel data. “Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems” . Convolutional neural networks have applications in image and video recognition, image classification, medical image analysis, natural language processing, and recommender systems. CNNs are also known as image processing and “artificial intelligence (AI) that use deep learning to perform both generative and descriptive tasks, often using machine vison that includes image and video recognition” (Rouse & Haughn).
Who, how, and when convolutional neural networks invented?
The very first Convolutional neural networks was invented by a Japanese computer scientist named Kunihiko Fukushima in 1982. It is known as Neocognitron. It is inspired by Hubel and Wiesel. The Neocognitron is a self-organizing artificial network of simple and complex cells which could recognize patterns. In 1989 a French scientist named Yann Lecun. He applied style learning algorithm to Neocognitron’s convolutional networks and released the LeNet5 which is the first modern convent that introduced some of the essential ingredients that we still use today. “In 2012, a team from the University of Toronto entered a convolutional neural network model (AlexNet) into the competition and that changed everything” (Demush 2019).
How do convolutional neural networks work?
CNNs work as artificial networks that have some type of specialization for being able to detect patterns and make sense of them. The patterns detection is what makes CNNs so useful for image analysis. Moreover, CNNs have hidden layers called convolutional layers and these layers are what make a CNN. The hidden layers receives input then transform the input in some way and then outputs the transform input to the next layer with a convolutional layer. This transformation with each convolutional layer specifies number of filters the layer should have. CNN with those filters can identify shapes, objects, texts, people, animals, and even organs.
A convolutional neural network consists of an input and an output layer, as well as multiple hidden layers. The hidden layers of a CNN typically consist of a series of convolutional layers that convolve with a multiplication or other dot product. The activation function is commonly a RELU layer, and is subsequently followed by additional convolutions such as pooling layers, fully connected layers and normalization layers, referred to as hidden layers because their inputs and outputs are masked by the activation function and final convolution. The final convolution, in turn, often involves backpropagation in order to more accurately weight the end product (Wikipedia 2019).
“Convolutional Neural Network.” Wikipedia, Wikimedia Foundation, 26 Oct. 2019, https://en.wikipedia.org/wiki/Convolutional_neural_network.
“Large-Scale Video Classification with Convolutional Neural Networks.” Large-Scale Video Classification with Convolutional Neural Networks (CVPR 2014), https://cs.stanford.edu/people/karpathy/deepvideo/. 
Rouse, Margaret, and Matthew Haughn. “What Is Convolutional Neural Network? – Definition from WhatIs.com.” SearchEnterpriseAI, https://searchenterpriseai.techtarget.com/definition/convolutional-neural-network.
Demush, Rostyslav. “A Brief History of Computer Vision (and Convolutional Neural Networks).” Hackernoon, 26 Feb. 2019, https://hackernoon.com/a-brief-history-of-computer-vision-and-convolutional-neural-networks-8fe8aacc79f3.