Deep Learning is not enough, and we need to start over -- Hinton confirms what I have been saying for two decades.https://www.axios.com/ai-pioneer-advocates-starting-over-2485537027.html …
-
Agree with limitations of various methodologies (deep learning, svms, etc), but Hinton not critiquing neural architectures, rather back prop
-
-
I don't think he was necessary critiquing large amounts of data, just large amounts of manually labeled data.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yup, though not neural nets. Current training schemas (back prop etc) only work with large amounts of labelled data. Can we imagine others?
- 1 more reply
New conversation -
-
-
The dirtyness of massive data may have unique uses where filtered/cleaned big data make it almost useless.So may not be always bad?
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.