As Asa H acquires a larger and broader case base memory it tends to attempt to attend to too many things at once. It may be possible to focus attention by only passing the N most activated concepts (outputs) from each layer of the hierarchy to the next (see my blog of 26 Aug. 2013, lines 1011-1013 of the code). What value should N have? Should it be different for different levels? Should it change as Asa learns more? If so, how should it change?
There is less of an issue for specialized Asa agents. A generalist supervisor (or network of supervisors) filters input and sends it to the appropriate specialist(s) for action.
The use of the right feature detectors and the right similarity measures should also help.
No comments:
Post a Comment