Artificial Consciousness/Neural Correlates/Neural Network Models

 Neural Network Models 

Neural Networks is the study of how neurons form networks and how the networks function.What scientists have found is that the storage within the network is intrinsic to the network, in a way that makes it a phenomenon of the network as a whole. Worse, network storage locations are sensitive to timing and other factors around the storage, and so even equivalent networks are often unique in their storage arrangements.

Neural Networks were popularized by the Connectionist school who thought they could derive some data about the way that networks connected, and figure out what the mathematical equivalence of each connection would be. However this was not to be. There was simply too much individuality between networks for there to be a commonality in connections.

The Selectionists took over from the connectionists, and were able to show that despite individualized connections, neurons in networks tended to self-select if the neurons were mutually inhibitive. The result was the recognition that neurons competed for attention.

The following models give a look at current network models, however it should be noted that as new discoveries are made these models might shift or skew in ways we cannot predict at the moment


 * The Instar Model
 * The Outstar Model
 * The Delay Line Model
 * The Neural Computation Model
 * The Input Layer
 * The Hidden Layer/s
 * The Output Layer
 * Learning new connections
 * Pruning Obsolete Connections