I tend to agree, but I am also still afraid that someone accidentally misconfigures the loss function of GPT-2 and instead of 20 layers of style it discovers five layers of meaning, and comes after us. :)https://twitter.com/dmonett/status/1212992388546932736 …
The priors are the result of an evolutionary search. Nothing a DL algorithm cannot do.
-
-
“Their words are referenced to how many times it appeared in the corpus“ ... in the context of cooccuring other words. And the same is true for the blips on your retina, skin or thalamus.
-
Given Neuroscience's perspective, I don't think we recognize things by the repeating pattern in single pixel value combinations. Yes, there are low representation of knowledge, but not single values. Another note is the ability to reflect back on the brain for a more complex […]
- 11 more replies
New conversation -
-
-
Josha, we have different definition of priors. That will spark a Bayesian statistics conversation that is irrelevant to your post. Like I always say, evolutionary algorithms, or any subset of Evolutionary Strategies (ES) are stochastic, and based on probability distribution […]
-
Of some random variable values. Again, so long as there is no grounded reference of deterministic knowledge from which stochastic events can take off, these approaches are very limited. What DL actually does (in CV & NLP) is capture spurious frequency based correlations.
End of conversation
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.