Neural network inspired from the human nervous system. It is based on a collection of connected units or nodes called artificial neurons. The approach original objective was to solve problems in the same way that a human brain would, and since then it has been used on a diversity of applications, including but not limited to medical diagnosis, speech recognition, computer vision, and social network filtering.
Yet another research area in AI, neural networks, is inspired from the natural neural network of human nervous system.
What are Artificial Neural Networks (ANNs)?
The inventor of the first neurocomputer, Dr. Robert Hecht-Nielsen, defines a neural network as −
"...a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.”
Basic Structure of ANNs
The idea of ANNs is based on the belief that working of human brain by making the right connections, can be imitated using silicon and wires as living neurons and dendrites.
The human brain is composed of 86 billion nerve cells called neurons. They are connected to other thousand cells by Axons. Stimuli from external environment or inputs from sensory organs are accepted by dendrites. These inputs create electric impulses, which quickly travel through the neural network. A neuron can then send the message to other neuron to handle the issue or does not send it forward.
Artificial neural networks are a scientific model that depends on the helpful sorts of human natural neural systems. Basically, a neural network involves prearranged and interrelated neurons that procedures the information by methods for connectionist technique for computation [25]. These are the essential electronic methods on the premise of neural advancement of brain. Brain on a very basic level gets information from learning. In this way, powerlessness of present PCs in settling particular issues might be settled with practical bundles. These approaches expect less specialized plans in developing machine solutions. The fundamental targets of these systems is to solve of the issues as brain does, which demands thousands excessively couple of a great many neural units and a large number of associations. ANNs procedure records everyone in turn, and learn via looking at the classification task of the record with the known right characterization of the record. The mistakes from the underlying classification of the principal record is fed back once again into the system, and utilized to alter the systems approach for advance iterations
Based on my studying, i can explain Artificial Neural Network (ANN) as, it is one of a powerful algorithms that is used in several works based machine learning and can be as Regression or Classification. And the ANN can learning by adjusting the parameters to reduce the discrepancy between the target output and each training case. in another hand, ANN structure which can be explain as, there is one axon that branches. In each neuron there is one axon that branches (sender), there is a dendritic tree(receiver) that collects input from other neurons. Axons is typically contact with dendritic tree at (Synapse). The transfer of the informations between the sender and receiver occur because of a spike of axon activity which create injected into post-synaptic neuron.
An artificial neural network (ANN) is a scientific model that works similarly to the human neural system. Basically, a neural network involves prearranged and interrelated neurons that process information for computation. These are the essential electronic methods for the neural advancement of the brain. The brain, on a very basic level, receives information from learning. In this way, the powerlessness of present PCs can be settled with practical bundles. These approaches expect less specialized plans to develop machine solutions. The fundamental target of these systems is to solve the problems of a large number of neural units and associations. ANN records each task in turn and learns by reviewing the classification process with respect to the known characteristics of the task.