But, the definition of "deep learning" isn't it "*deep neural network
*learning" ? The word "deep" doesn't mean "extensive learning" or "learn
with much effort" (/sorry, don't know the exact term, I'm french
speaking people/). The word means "network with many layers". So, "deep
learning" is necessary neural network.
LAU
Le 12/01/2016 02:19, Jim Bromer a écrit :
I am listening to the Pesenti Tedx talk. Thanks again for telling me
about it. I have learned something this morning.
I do not agree that Deep Learning necessarily refers to a Neural
Network method. I feel that Watson-Jeopardy was a deep learning system
because it created hypotheses and then looked for evidence to support
them. This step is a learning step. And of course it acted on an
extensive corpus. However, if the conventional definition of "Deep
Learning" becomes associated with the use of a neural network as a
required part of the system I will go along with it. However, I do not
think that that meaning will prevail. So at this time I feel that
Watson-Jeopardy is an example of Deep Learning even though it might
not have been the poster child of Deep Learning.
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/27172223-36de8e6c
Modify Your Subscription: https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com
-------------------------------------------
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
