ntm-one-shot icon indicating copy to clipboard operation
ntm-one-shot copied to clipboard

Published 20 hours ago • verified publisher icon tristandeleu

Persistent memory

Open sheetalreddy opened this issue 7 years ago • 1 comments

Hi , In the paper , they mentioned a paragraph about persistent memory and the results they got with them. I was wondering about how to keep the external memory persistent and not wipe it off across episodes if i have a different label space across episodes . Is it even possible to work it around in such a way ?

sheetalreddy avatar Jan 10 '18 05:01 sheetalreddy

Hi! Here I am indeed resetting the memory at the beginning of each episode. To have a persistent memory across episodes, you can turn the initial memory M_0 into a tensor, and return the final memory state in memory_augmented_neural_network (maybe l_ntm_var[0][-1]).

Let me know if you have any trouble making that change.

tristandeleu avatar Jan 10 '18 13:01 tristandeleu