Approaching an unknown communication system by latent space exploration and causal inference
arxiv(2023)
摘要
This paper proposes a methodology for discovering meaningful properties in
data by exploring the latent space of unsupervised deep generative models. We
combine manipulation of individual latent variables to extreme values with
methods inspired by causal inference into an approach we call causal
disentanglement with extreme values (CDEV) and show that this method yields
insights for model interpretability. With this, we can test for what properties
of unknown data the model encodes as meaningful, using it to glean insight into
the communication system of sperm whales (Physeter macrocephalus), one of the
most intriguing and understudied animal communication systems. The network
architecture used has been shown to learn meaningful representations of speech;
here, it is used as a learning mechanism to decipher the properties of another
vocal communication system in which case we have no ground truth. The proposed
methodology suggests that sperm whales encode information using the number of
clicks in a sequence, the regularity of their timing, and audio properties such
as the spectral mean and the acoustic regularity of the sequences. Some of
these findings are consistent with existing hypotheses, while others are
proposed for the first time. We also argue that our models uncover rules that
govern the structure of units in the communication system and apply them while
generating innovative data not shown during training. This paper suggests that
an interpretation of the outputs of deep neural networks with causal inference
methodology can be a viable strategy for approaching data about which little is
known and presents another case of how deep learning can limit the hypothesis
space. Finally, the proposed approach can be extended to other architectures
and datasets.
更多查看译文
关键词
latent space exploration,causal inference,communication system,unknown communication system
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要