dnc
dnc copied to clipboard
A TensorFlow implementation of the Differentiable Neural Computer.
Dear author: We notice that in the paper, the memory is a 2D matrix (cell number, memory size]), but in pratice, the memory is a 3D tensor ([batch size, cell...
I ran `ipython3 train.py ` I got this: ![screenshot from 2018-11-04 21-33-29](https://user-images.githubusercontent.com/7977794/47974839-6da51480-e079-11e8-8e88-966c6ae66762.png) I installed sonnet from this command `$ pip install dm-sonnet`
Upgrades repo from TF1 to TF2 while preserving the core design and logic. Quality of life: Formally separated unit testing Added requirements.txt Added precommit hooks for style Repeat Copy training...
I am very interested in this part of the experiments with Mini-SHRDLU, which inspired our current work. So, I would like to ask the author whether the code of this...
Hi, Are the _Family Tree_ and _London Underground_ datasets mentioned in the paper openly available? If so, where can I find them? Thanks, Thiviyan
I wonder to know how can I create placeholders like dnc_core.initial_state(batch_size=n) with the batch_size n changed in trainning. > dnc_core = dnc.DNC(...) > initial_core_state = dnc_core.initial_state(batch_size=1) > core_state_placeholders = snt.nest.map(lambda...
Is there any example implementation for block puzzle game using reinforcement learning?
I would like to ask if there is a formal description of the multiple write head case, as this case is not presented in the original paper.
I just made this into a package that can be installed via pip. Thought it was a simple and useful enough change that you might be happy to merge it!...