Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations — mentioned by naasking

Mon, 13 Mar 2023 01:22:36 GMT

> A TM cannot learn an arbitrary CFG. It needs constraints. Well sure, because CFGs can have unbounded depth, and all real brains are finite. But they can learn bounded CFGs: https://arxiv.org/abs/2112.09174 > Our brains are much more complex than an artificial NN, though. Yes, brains have a few orders of magnitude more parameters, and lots of evolutionary baggage. It's not clear how many parameters would be needed without that evolutionary baggage. Time will tell. > So the mere thought that the two somehow share functionality after a wildly different learning process is somewhat far-fetched.…

Paper and discussion history. A mention is not an endorsement.

Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations · HackerPapers discussions

Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations — mentioned by naasking