When a neuron is stimulated, it will fire it's spikes somewhen in the next milliseconds and seconds. It will never be exactly at the same time. In combination with millions or billions other neurons, this causes an interference.
The same stimulation will lead to a distinct chain of association every time. It will never be the same, because of interference.
Mittwoch, 11. April 2012
Dienstag, 10. April 2012
AI requires 3 things
(1) Neuron Model
(2) Topology
(3) Complexity
The model of an isolated neuron is everything. There is no supervision. This is, because supervising or logging the work of 100 billion neurons would be more complex than 100 billion neurons. Then you need topology and then (more and enough) complexity.
Model the neuron in the scope of seconds and hours.
Model short time spontaneous firing.
Model awakeness and sleep.
Model dreaming (long time spontaneous firing caused by stimulation hours ago).
(2) Topology
(3) Complexity
The model of an isolated neuron is everything. There is no supervision. This is, because supervising or logging the work of 100 billion neurons would be more complex than 100 billion neurons. Then you need topology and then (more and enough) complexity.
Model the neuron in the scope of seconds and hours.
Model short time spontaneous firing.
Model awakeness and sleep.
Model dreaming (long time spontaneous firing caused by stimulation hours ago).
Abonnieren
Posts (Atom)