Hacker News new | ask | show | jobs
by 0xdeadbeefbabe 3543 days ago
> a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols

A neural network without memory can't do that or can't do it as well perhaps?

1 comments

In fig. 5a, they compare its performance to that of an LSTM trained on the same problem, and it does seem to do much better.
I am guessing for an LSTM based neural network to learn memory sequencing for the purpose of solving problems will need a much deeper and wider network which a separate memory block tries to provide with ready made logic and much simpler network so it doesn't have to learn those actions.