Artificial neural networks (ANN) or connectionist systems are computer systems inspired by the biological neural networks that make up the brains of animals. Such systems learn (progressively improve performance) tasks by considering examples, generally without task-specific programming. For example, in image recognition, they could learn to identify images that contain cats by analyzing sample images that have been manually labeled as "cat" or "no cat" and using the results to identify cats in other images. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an original essay They do this without any prior knowledge about cats, such as that they have fur, tails, whiskers, and cat-like faces. Instead, they evolve their own set of relevant characteristics from the educational material they develop. An ANN is based on a set of connected units or nodes called artificial neurons (analogous to biological neurons in an animal's brain). Each connection (analogous to a synapse) between artificial neurons can transmit a signal from one to the other. The artificial neuron that receives the signal can process it and then signal to the artificial neurons connected to it. In common ANN implementations, the signal at a connection between artificial neurons is a real number, and the output of each artificial neuron is calculated from a nonlinear function of the sum of its inputs. Neurons and artificial connections typically have a weight that adapts as learning proceeds. Weight increases or decreases the signal strength at a connection. Artificial neurons can have a threshold such that only if the aggregate signal exceeds that threshold is the signal sent. Typically, artificial neurons are organized into layers. Different layers can perform different types of transformations on their inputs. The signals travel from the first level (input) to the last (output), possibly after crossing the levels several times. Please note: this is just an example. Get a custom paper from our expert writers now. Get a Custom Essay The original goal The ANN approach was to solve problems the same way a human brain would. Over time, attention has focused on matching specific mental abilities, leading to deviations from biology. ANNs have been used in a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, board and video games, and medical diagnosis.