# deepmind/dnc

A TensorFlow implementation of the Differentiable Neural Computer.
161 次浏览

# Differentiable Neural Computer (DNC)

This package provides an implementation of the Differentiable Neural Computer, as published in Nature.

Any publication that discloses findings arising from using this source code must cite “Hybrid computing using a neural network with dynamic external memory", Nature 538, 471–476 (October 2016) doi:10.1038/nature20101.

## Introduction

The Differentiable Neural Computer is a recurrent neural network. At each timestep, it has state consisting of the current memory contents (and auxiliary information such as memory usage), and maps input at time t to output at time t. It is implemented as a collection of RNNCore modules, which allow plugging together the different modules to experiment with variations on the architecture.

• The access module is where the main DNC logic happens; as this is where memory is written to and read from. At every timestep, the input to an access module is a vector passed from the controller, and its output is the contents read from memory. It uses two futher RNNCores: TemporalLinkage which tracks the order of memory writes, and Freeness which tracks which memory locations have been written to and not yet subsequently "freed". These are both defined in addressing.py.

• The controller module "controls" memory access. Typically, it is just a feedforward or (possibly deep) LSTM network, whose inputs are the inputs to the overall recurrent network at that time, concatenated with the read memory output from the access module from the previous timestep.

• The dnc simply wraps the access module and the control module, and forms the basic RNNCore unit of the overall architecture. This is defined in dnc.py.

## Train

The DNC requires an installation of TensorFlow and Sonnet. An example training script is provided for the algorithmic task of repeatedly copying a given input string. This can be executed from a python interpreter:

$ipython train.py You can specify training options, including parameters to the model and optimizer, via flags: $ python train.py --memory_size=64 --num_bits=8 --max_length=3

# Or with ipython:
\$ ipython train.py -- --memory_size=64 --num_bits=8 --max_length=3

Periodically saving, or 'checkpointing', the model is disabled by default. To enable, use the checkpoint_interval flag. E.g. --checkpoint_interval=10000 will ensure a checkpoint is created every 10,000 steps. The model will be checkpointed to /tmp/tf/dnc/ by default. From there training can be resumed. To specify an alternate checkpoint directory, use the checkpoint_dir flag. Note: ensure that /tmp

deepmind
• 最近提交：2019-04-18
• 创建时间：2017-03-28