Neurons are the basic building block our brain. It has been estimated that the average human brain contains about 100 billion neurons and, on average, each neuron is connected to 1000 other neurons. This results in the generation of vast and complex neural networks that are the mainstay of the brain’s processing capabilities.
Neurons are the basic data processing units, the ‘chips’, of the brain. Each neuron receives electrical inputs from about 1000 other neurons. Impulses arriving simultaneously are added together and, if sufficiently strong, lead to the generation of an electrical discharge, known as an action potential (a ‘nerve impulse’). The action potential then forms the input to the next neuron in the network.
The functionality of these neurons make the human intelligent. It can be possible to mathematically model the functions of a single Neuron or the Entire neural network and code then up in a computer. these types of programs are known as Artificial Neural Networks. An Artificial Neural Network can learn itself or can be trained to do some work.
One interesting problem in Satellite Engineering is controlling a satellite on space. Its difficult to program a satellite to perform on space, because all the disturbances on space are not known to Human. Therefore, an Artificial Neural Network controlled spacecraft perform better on space because it can learn from its surroundings without any human input and control its own behavior.
An artificial neural network controlled spacecraft control system is proposed by a student and two professors from IIT Kgp and Mc Gill University. They claim that their Dynamic Neural Network controlled attitude control system in much robust than the standard PD or PID control system as it can adapt itself to any unknown disturbance torque in space.
The detailed of their research work can be found in : http://arc.aiaa.org/doi/abs/10.2514/1.54408?journalCode=jgcd