Open amaneureka opened 8 years ago
Possible solution: push 'y' coordinate also in the input matrix, And let the network handle everything else. ;-)
Changes should include, number of neurons in input layer, array push (y-pos feature) and maybe number of neurons in hidden layers.
Current network works on object coming towards it, It does not care what is the 'Y-Pos' of it. Add this feature to network and enable 'PTERODACTYL' for testing.