Causal functions of sequences occur throughout computer science, from theory to hardware to machine learning. Mealy machines, synchronous digital circuits, signal flow graphs, and recurrent neural networks all have behaviour that can be described by causal functions. In this work, we examine a differential calculus of causal functions which includes many of the familiar properties of standard multivariable differential calculus. These causal functions operate on infinite sequences, but this work gives a different notion of an infinite-dimensional derivative than either the Fr\'echet or Gateaux derivative used in functional analysis. In addition to showing many standard properties of differentiation, we show causal differentiation obeys a unique recurrence rule. We use this recurrence rule to compute the derivative of a simple recurrent neural network called an Elman network by hand and describe how the computed derivative can be used to train the network.
翻译:从理论到硬件到机器学习,整个计算机科学中都存在序列的因果功能。机器、同步的数字电路、信号流图和经常性神经网络都具有因果功能所描述的行为。在这项工作中,我们检查了因果函数的不同计算法,其中包括标准的多变差异计算法的许多熟悉特性。这些因果函数以无限序列运作,但这项工作给出了与功能分析中使用的Fr\'echet或Gateaux衍生物不同的无限层面衍生物概念。除了显示许多标准差异特性外,我们还显示因果差异符合一个独特的重复规则。我们使用这种重复规则来计算称为 Elman 网络的简单经常性神经网络的衍生物,并描述如何用计算衍生物来培训网络。