论文标题
带有内存恶魔的可区分神经计算机
Differentiable Neural Computers with Memory Demon
论文作者
论文摘要
可区分的神经计算机（DNC）是一个神经网络，具有外部内存，可以通过读取，写入和删除操作进行迭代内容修改。 我们表明，内存内容的信息理论属性在此类体系结构的性能中起着重要作用。我们将记忆恶魔的新颖概念介绍给DNC体系结构，该架构通过加法输入编码隐式修改内存内容。内存恶魔的目标是最大化连续外部内存内容的相互信息的预期总和。
A Differentiable Neural Computer (DNC) is a neural network with an external memory which allows for iterative content modification via read, write and delete operations. We show that information theoretic properties of the memory contents play an important role in the performance of such architectures. We introduce a novel concept of memory demon to DNC architectures which modifies the memory contents implicitly via additive input encoding. The goal of the memory demon is to maximize the expected sum of mutual information of the consecutive external memory contents.
