While I admire the work of @GaryMarcus in fleshing out the inadequacies of #DeepLearning, I completely disagree with him that DL just needs to be augmented in some manner. DL must be completely thrown out like yesterday's garbage if AGI research is to make any progress.https://twitter.com/GaryMarcus/status/959459804199735296 …
-
-
I think the main problem of deep learning is not what it is, but the problems that it tries to solve. Assigning human level understanding to a picture based on labeled dataset of millions of photos without embodied experience is just too much of shortcut.
-
The main reason I maintain that DL must be discarded is that DL learns complex patterns but the brain does not. The brain can instantly see a new complex pattern without learning it. There aren't enough neurons and synapses in the brain to store all possible patterns like DL.
- 2 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.