What are artificial neural networks?

Artificial neural networks (ANN) is an attempt to imitate the network of neurons that comprise the human brain in a computer, so that the computer can learn to make decisions much in the way that humans do. The purpose is so that computers can begin to reason in the same way that humans do. While it seems like a simple concept, the way it works is actually a bit more complicated.

This is done through mathematical processing that helps ANNs makes sense of the information that is given to it. One ANN has between 12 to millions of artificial neurons (units) that are layered.

This layer receives input from the outside world, and this data is the one it wishes to learn about. The data goes to one or more hidden units from the input unit, and then the hidden unit translates this information into something that the output unit can use.

The units are layered, and the connections are weighted. The higher the number the greater the influence one unit has on another, and this akin to the way the human brain works.

Meanwhile, as this data passes through one unit, the brain is learning more and more. The output data is where the network data is entered and processed. This whole concept is based off the fact that the human brain processes information hierarchically.

Artificial Neural Networks (ANN) are computing systems used for many different learning algorithms to process complex data. ANN is based on the structure and function of biological neural networks (thought to be inspired by the human brain). It consist of input and output layer as well as a hidden layer.

ANN is based on a collection of connected units or nodes known as artificial neurons, these artificial neurons model the neurons in a biological brain. Each connection can transmit signal from one artificial neuron to another. The goal of ANN is to solve problems just the way the human brain would. It has been used in many spheres of life - speech recognition, medical diagnosis, computer vision and many others.