arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.09002cs.NE
收藏

数据流矩阵机作为循环神经网络的推广

Dataflow Matrix Machines as a Generalization of Recurrent Neural Networks

Michael Bukatin, Steve Matthews, Andrey Radul

摘要:

数据流矩阵机器是循环神经网络的一个强大的推广。它们可以处理多种类型的任意线性流,多种类型的强大神经元,并允许合并高阶结构。我们希望它们在机器学习和概率编程中,以及在动态系统和确定性和概率性程序的合成中是有用的。

英文摘要:

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of arbitrary linear streams, multiple types of powerful neurons, and allow to incorporate higher-order constructions. We expect them to be useful in machine learning and probabilistic programming, and in the synthesis of dynamic systems and of deterministic and probabilistic programs.

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。

↑