"It is important, both for intellectual honesty and for continued funding, that AI researchers claim credit for our successes and take ownership of our shortcomings." Completely agree w above (but also never said deep learning should be abandoned)https://medium.com/@tdietterich/what-does-it-mean-for-a-machine-to-understand-555485f3ad40 …
-
i would call your attention to the conclusions page 171, particularly last few sentences in the screenshot, “symbols-manipulation [does not likely] exhaust the components for cognition.... multilayer perceptrons may play a role ... provide excellent models [of some phenomena”pic.twitter.com/FnKRO5F2Ox
you are just making that up. read this: https://journals.sagepub.com/doi/10.1111/1467-8721.00080?icid=int.sj-abstract.similar-articles.3 … or any thing pinker and i wrote about hybrid models for past tense of english
-
-
I understand the argument that the neural networks of 2000 weren't enough. I also agree that deep learning of 2019 is not everything. But you have claimed in 2001 in your book was that connectionism of the back-propagation kind was a *small corner* of the entire space.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.