Posts

Showing posts with the label AGI

Artificial General Intelligence - The Feathers Problem

Just a simple thought: The Feathers Problem One of the challenges in the invention of powered flight was deciding what matters most.  If one wants to imitate birds there are many factors: Wing curvature Wing warping or twist Flapping Feathers Jumping into flight from the ground Energy source and many more. Some early pioneers of flight proposed feather covered wings.  After all, that is what birds have.  Flapping was tried also. In the end the Wright Brothers figured out that the salient factors were lift, drag, thrust, and weight. The lift was generated by wing curvature, not the fact there were feathers. So the first working airplane (and first gliders that worked) did not have feathers. The other solutions they came up with were light weight engine, wing warping (flaps came later) for control, no flapping but instead propellers, linear sliding take off rather than a jump, solved the learning cure issue with learning to fly a craft without any craft worki...

Avalanche Pattern Recognition

One feature of an SRS (see previous post) is that the 3D regular array of neurons (the cortex) can recognize a fragmented pattern in the subsumptive system, stimulate the subsumptive system into that pattern to a small degree, and then on the next time tick, recognize the now stronger pattern and repeat the process.  The entire system will rapidly avalanche into the state where the pattern is fully matched and the subsumptive system is fully in the match state. This system will then be locked into that state. Several factors can get the system out of the state and allow 'thinking' to continue. The pattern matcher will recognize the locked in state and begin predicting the next state. If one simulates the neurons getting 'tired' or 'bored' they can stop matching the locked in state and more easily match to the next state.  I call this Neural Fatigue.  An analog in biological neurons is the refractory period (maybe). Some external stimulus to the system li...