Deep learning has made significant advances in creating efficient representations of time series data by automatically identifying complex patterns. However, these approaches lack interpretability, as the time series is transformed into a latent vector that is not easily interpretable. On the other hand, Symbolic Aggregate approximation (SAX) methods allow the creation of symbolic representations that can be interpreted but do not capture complex patterns effectively. In this work, we propose a set of requirements for a neural representation of univariate time series to be interpretable. We propose a new unsupervised neural architecture that meets these requirements. The proposed model produces consistent, discrete, interpretable, and visualizable representations. The model is learned independently of any downstream tasks in an unsupervised setting to ensure robustness. As a demonstration of the effectiveness of the proposed model, we propose experiments on classification tasks using UCR archive datasets. The obtained results are extensively compared to other interpretable models and state-of-the-art neural representation learning models. The experiments show that the proposed model yields, on average better results than other interpretable approaches on multiple datasets. We also present qualitative experiments to asses the interpretability of the approach.

翻译：深度学习通过自动识别复杂模式，在创建时间序列数据的有效表示方面取得了显著进展。然而，这些方法缺乏可解释性，因为时间序列被转换为难以解读的潜在向量。另一方面，符号聚合近似（SAX）方法能够创建符号化表示并具有解释性，但无法有效捕捉复杂模式。本研究针对单变量时间序列的可解释神经表示提出了一套需求标准，并设计了一种满足这些需求的新型无监督神经架构。该模型能够生成一致性、离散性、可解释且可视化的表示。为确保鲁棒性，模型在无监督环境下独立于下游任务进行学习。为验证模型有效性，我们基于UCR存档数据集在分类任务上开展了实验，并将结果与同类可解释模型及前沿神经表示学习模型进行了广泛对比。实验表明，该模型在多个数据集上的平均性能优于其他可解释方法。此外，我们通过定性实验评估了该方法的可解释性。