Neural Networks or Artificial Neural Networks (ANNs) are computational models which simulate the connectivity of the neuronal structure of cerebral cortex and the brain learning patterns for certain computational tasks, such as machine learning, cognitive and pattern recognitions, etc.. Conventional computational models usually fare poorly in these areas.
Differing from Computational Neuroscience which offers in-depth study of the true complex biological neuronal functions in information processing in the brain, a neural network is more a simplified modeling technique or a set of algorithms in simulating the patterns of stimulations and repetitive learning of the brain by using interconnected parallel computational nodes as artificial neurons that are often organized into inputs, outputs and processing layers. Adaptive weights are used to simulate the connection strength between any two neuron nodes. Theses weights can be adjusted repeatedly by each “learning” cycle instead of being determined beforehand.
There are many college courses designated to the study of Neural Networks. In a simple sense, neural networks offer the possibility of continued learning and corrections in order to eventually fit the models closer to a particular function of the brain by comparing the outcomes to a certain reality. This is a huge deviation from the conventional computational models. Conventional models are deterministic with data and pre-defined instruction sets stored in memory for a centralized processor node to retrieve, compute and store in a sequential manner to generate outcomes. However the processing nodes for neural networks get information from input nodes or external signals to carry out simple weighted computations in parallel and the results are together presented as the outcome. The knowledge of a neural network is in the entire network itself instead of in any single node. Each computational cycle is almost a self-learning and reality-adjusting cycle, similar to the way humans or animals generally learn.
A human brain contains billions of neurons, more than any other species on earth. Today, a typical large ANN may use a few thousands processor units as nodes, a much smaller number in comparison. With greatly enhanced computing power in cloud-ready world, the number of artificial neurons could be affordably extended if needed. However there is no such proven law yet whether a ANN’s power and reality-rendering accuracy are in direct proportion to the numbers of nodes it runs on. There is still a long way to go in AI to use ANN-enabled systems as the intelligent brains for everything in the plan, but we seem to be at least on the right track.