论文标题
深度卷积网络中的基于身份的模式：生成对抗性语音和重复性
Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication
论文作者
论文摘要
本文模拟了对基于身份的模式（或复制）的无监督学习，该语音中具有深厚卷积神经网络的原始连续数据的重复。我们使用Ciwgan ArchitectureBeguš（2021a; Arxiv：2006.02951），其中在语音中学习有意义的表示形式是从CNN产生信息性数据的要求中出现的。我们提出了一项技术，以使经过语音训练的CNN进行wug测试，并根据四个生成测试，认为该网络学会在其潜在空间中代表基于身份的模式。通过在潜在空间中仅操纵两个分类变量，我们可以将未重复的形式积极地变成重复的形式，而大多数情况下的产出没有其他实质性变化。我们还认为，网络将基于身份的模式扩展到未观察到的数据。探索CNN中基于身份的模式的有意义表示以及训练范围之外的潜在空间变量如何与输出中的基于身份的模式相关联有对神经网络可解释性的一般影响。
This paper models unsupervised learning of an identity-based pattern (or copying) in speech called reduplication from raw continuous data with deep convolutional neural networks. We use the ciwGAN architecture Beguš (2021a; arXiv:2006.02951) in which learning of meaningful representations in speech emerges from a requirement that the CNNs generate informative data. We propose a technique to wug-test CNNs trained on speech and, based on four generative tests, argue that the network learns to represent an identity-based pattern in its latent space. By manipulating only two categorical variables in the latent space, we can actively turn an unreduplicated form into a reduplicated form with no other substantial changes to the output in the majority of cases. We also argue that the network extends the identity-based pattern to unobserved data. Exploration of how meaningful representations of identity-based patterns emerge in CNNs and how the latent space variables outside of the training range correlate with identity-based patterns in the output has general implications for neural network interpretability.
