Although I did not think it was going to happen this way, it makes
sense that relatively simple applications of neural networks would
make a number of advances in AI at this time. The neural network is a
simple concept. I am surprised by how well Deep Learning does work for
some applications. The merging of probabilities is also (can be kept
to) a (relatively) simple network. I think Conceptual Networks, which
would be much more complex could have the ability to go way beyond
today's Deep Learning. If this analysis is right, then a relatively
simple Conceptual Network should be both more sophisticated than Deep
Learning and feasible at this time.
Jim Bromer


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to