使用神经堆栈的上下文无关转换
Context-Free Transductions with Neural Stacks
摘要：
本文分析了堆栈增广递归神经网络（RNN）模型的行为。由于堆栈RNN和下推传感器之间的架构相似性，我们在许多任务上训练堆栈RNN模型，包括字符串反转，上下文无关语言建模和累积XOR评估。检查我们的网络的行为，我们表明堆栈增强的RNN可以发现直观的基于堆栈的策略来解决我们的任务。然而，堆栈RNN比LSTM等经典架构更难训练。更复杂的网络通常使用堆栈作为非结构化存储器来找到近似解，而不是使用基于堆栈的策略。
英文摘要：
This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more complex networks often find approximate solutions by using the stack as unstructured memory.
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。
