RW: I guarantee your brain was using some tightly constrained learning
algorithm with very few free variables or the process would have been
interrupted, not only by the loss of vision, but by the heat-death of the
universe.
I hope that’s not a moneyback guarantee. Do you think there’s an algorithm
that can calculate every object you’re likely to handle, and determine your
grasp for every new object you encounter? Handling and vision are
interdependent. Hence “do you grasp what you see?”
https://www.google.co.uk/search?q=%22grasp+what+you+see%22&sugexp=chrome,mod=4&sourceid=chrome&ie=UTF-8
About 385,000 results
Both have to be done very rapidly. There is no time to go through a systematic
set of variables.
And as for there being a limited set of “very few free variables “ (or any set
of variables) that determine object form, well we’d all love to hear what they
might be....
It’s much more likely that object recognition and object handling both work by
an interdependent process of “groping” – rapidly “having a stab” at an
approximate object grasp (for handling) or object template (for recognition),
and then adjusting/shifting as needed to more tightly “fitting” grasps/
templates – this being an “analogous”/mapping business. Rational algorithmic
solutions are right or wrong, creative solutions are more or less “fitting” to
the requirements – “fit for purpose.”
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com
