Artificial neural network

Neural network is modeled loosely on the Human brain, which helps computer to learn from being fed data. This powerful branch of learning is efficient, more than anything. This artificial neural network can be taken as one of the most disruptive technologies that exist today. One of the earlier ideas about AI was that if enough information is fed to the computer and all possible directions are give it as possible then it will be able to "think". But with this sort of computing the machine relies on fixed rules. A simple and systematic way of analyzing input data that loosely modeled after human thinking, has been resurrected. An artificial neural network (ANN) is an algorithmic construct that enables machine to learn everything from voice commands and playlist curation to music composition and image recognition. The typical ANN consist of thousands of interconnected artificial neurons, which are stacked sequentially in rows that are known as layers, forming millions of connections. In many cases, layers are only interconnected with the layers of neurons before and after them via inputs and outputs. This layered ANN is one of the main ways to go about machine learning today, and feeding it vast amount of labeled data enables it to learn how to interpret that data like Human. Convulation neural network or CNN is responsible for image recognition, the name is given as it use a mathematical process known as convulation. This convulation is able to analyze images in a non-literal ways e.g. identification of a partially obscure object or one that is viewed from certain angles. Neural network is feed with vast amount of data, labeled by humans so that neural network can essentially fact-check itself as it's learning. This learning is known as supervised learning. The convulation neural network is composed of four layers: convulation, activation, pooling, fully connected.
https://techcrunch.com/2017/04/13/neural-networks-made-easy/