Deep learning more and more looks like a scientific revolution in the sense of Thomas Kuhn. As exciting as seeing engineering successes, is to experience first hand how a research field goes through a “paradigm shift”.
Show this thread
-
We looked at a simple arithmetic task with addition, substraction and brackets. Simple, but an infinite domain and clearly compositional. Networks approximate answers within training range almost perfectly, generalize quite well, with errors increasing with length of expressions.
-
-
I read the prediction of the '99 ABA/ABB paper (and Algebraic Mind) as anticipating the failure of non-symbolic-NNs in generalizing outside of the training space (i.e. not being able to account for rules/hierarchy/composition)
-
And was that prediction correct? For the summary above, it seems like it.
- 10 more replies
New conversation -
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.