What is an artificial neural network?

The artificial neural network is the name for a certain type of computer technology that seeks to imitate the human brain. The artificial neural network or Ann includes simulated neurons and stimuli for attempts to reproduce brain functions. This wide range of software and devices uses models of nerve algorithms to create decision -making processes that planners hope to carefully mimic human thinking processes. Artificial neural networks represent a great progress from relatively primitive ideas about computers in previous decades.

Neural Network Software is traditionally applied to playing games and other tasks that include relatively calculated human thinking. In the biophysical sense, neuron networks are based on exploring how brain neurons communicate and pass on reports. Neuron network applications include the interaction of various functions where engineers look at the overall productive output to see how these artificial neural network systems can affect the human idea. Different “applicationsin real life ”for Ann include regression analysis, function approximation, robotics and general data processing.

For different research provisions, different types of artificial neural networks have been developed. These use different types of learning models such as supervision, unattended or reinforced learning. Neuron network types include a one -way feeding network, radial basic functions or RBF network, a self -service Kohonen network and even modular neuron networks, where a larger net is composed of several small.

6 This is also sometimes called an associative neural network or ASNN. The advantage of this kind of research is obvious to engineers who believe that ASNN can help model decision -making on a human group or other comprehensive modeling in some similar ways to individual models of decision -provided Ann.

Principle that is often used by an artificial neural network is called "fuzzy logic". The word "fuzzy" is used to describe all gaps in data or knowledge. Neuron networks are often able to close some gaps in the field of data or knowledge by educated guessing and statistical predictions, which, unlike strict binary logic, is "yes or no" traditionally associated with electronic decision -making. Overcoming fuzzy logic helps neural networks provide better results in simulations. The use of building blocks of previous research, planners and engineers who have experience with artificial neural networks are constantly increasing what these tools can do to move our knowledge of our own minds.