Hmm. It’s not that NNs claim to abstract a complete knowledge of how brains work. Box & Cox: All models are wrong. The question is - how wrong does a model have to be, to not be useful?https://twitter.com/GaryMarcus/status/1200088188934451200 …
Replying to @anilkseth
GPT-2 is so wrong as model of natural language understanding it is diverting from real questions that need to be answered (eg how does a listener construct a model of what speaker is trying to say). people should recognize limits & move on. instead they collect bigger data sets.
2:43 PM - 28 Nov 2019
0 replies
0 retweets
2 likes
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.