search

ixaxaar / pytorch-dnc

Differentiable Neural Computers, Sparse Access Memory and Sparse Differentiable Neural Computers, for Pytorch
MIT License
335 stars 56 forks source link

And the confusion about w_write #34

Open wjbianjason opened 5 years ago

wjbianjason commented 5 years ago

I find w_write(t) = w_read(t-1) + w_lt(t), why use t-1 timestep read weight rather than t timestep read weight, I think w_read(t) is more related to w_write(t), is there some consideration ? thanks