Re:Deep Learning With Commodity Off-The-Shelf High Performan...
by waps on Tuesday June 18, 2013 @03:57AM
(#5898097)
The great thing about pulse-based neural networks (like a human brain) is that latency, as long as it's constant, is not an issue. In fact you'd want connections with a wide variety of different latencies. They should be random, but remain constant over the life of the simulation.
Plus you have to keep in mind that this is a simulation. Computer can't keep up ? Run it at half "real-time".
Plus you have to keep in mind that this is a simulation. Computer can't keep up ? Run it at half "real-time".