论文标题
使用状态合并从RNN中提取有限自动机
Extracting Finite Automata from RNNs Using State Merging
论文作者
论文摘要
解释黑框复发性神经网络（RNN）的行为的一种方法是从中提取出更容易解释的离散计算模型，例如有限状态机，可以捕获其行为。在这项工作中，我们提出了一种新方法，用于从由状态合并语法推断的状态合并范式启发的RNN中提取有限自动机。我们证明了我们的方法对tomita语言基准的有效性，在那里我们发现它能够从接受基准中所有语言的RNN中提取忠实的自动机。我们发现，提取过程中提供的数据数量得到了提取性能，以及奇怪的是，在完美学习其目标语言之后，RNN模型是否经过培训。我们使用我们的方法来分析这种现象，发现超越收敛的训练是有用的，因为它会导致RNN内部状态空间的压缩。这一发现表明，我们的方法如何用于解释性和分析经过训练的RNN模型。
One way to interpret the behavior of a blackbox recurrent neural network (RNN) is to extract from it a more interpretable discrete computational model, like a finite state machine, that captures its behavior. In this work, we propose a new method for extracting finite automata from RNNs inspired by the state merging paradigm from grammatical inference. We demonstrate the effectiveness of our method on the Tomita languages benchmark, where we find that it is able to extract faithful automata from RNNs trained on all languages in the benchmark. We find that extraction performance is aided by the number of data provided during the extraction process, as well as, curiously, whether the RNN model is trained for additional epochs after perfectly learning its target language. We use our method to analyze this phenomenon, finding that training beyond convergence is useful because it leads to compression of the internal state space of the RNN. This finding demonstrates how our method can be used for interpretability and analysis of trained RNN models.
