casual_slacker
Joined 13 years ago
Joined 13 years ago
Is this functionally equivalent to having a two layer mini-network (that represents one brain neuron), with one neuron on top, and "child" neurons on bottom that mimic the grouping behavior? If this is true, then I would suspect our networks are already doing something like this automatically.
These aren't discarded, they are part of ML vision networks today. Edges are one of the 3x3 convolutions that a network can learn, SIFT/etc are the dense / clustering nets, I'll admit I just googled Generalized Cylinders (very interesting). There are others like SLAM as well.
I imagine generalizing this, not just "fcontrol" but other information-awaiters, it would be like functions wrapped in decorators of the various yield-channels they can emit to. Probably someone already does this.