作为线性流计算模型的数据流矩阵机
Dataflow Matrix Machines as a Model of Computations with Linear Streams
摘要:
我们概述了递归神经网络的图灵完全推广和作为一个编程平台的鲁棒矩阵机。我们描述了向量空间的有限前缀树的数值叶,使我们能够结合表达能力的低矩阵机器与简单的传统递归神经网络。
英文摘要:
We overview dataflow matrix machines as a Turing complete generalization of recurrent neural networks and as a programming platform. We describe vector space of finite prefix trees with numerical leaves which allows us to combine expressive power of dataflow matrix machines with simplicity of traditional recurrent neural networks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。