Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes.
Neural Computation(2018)
摘要
We extend the neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing trainable address vectors. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies, including both linear and nonlinear ones. We implement the D-NTM with bot...
更多查看译文
关键词
dynamic neural turing machine,discrete addressing schemes
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络