Finding the DeepDream for Time Series: Activation Maximization for Univariate Time Series
This work addresses interpretability for time series models in safety-critical domains like healthcare, but it is incremental as it adapts an existing method to a new data type.
The authors tackled the challenge of interpreting neural networks for univariate time series by introducing Sequence Dreaming, an adaptation of Activation Maximization with regularization techniques like exponential smoothing, which generated targeted sequences for classification tasks in predictive maintenance, demonstrating versatility in uncovering temporal features.
Understanding how models process and interpret time series data remains a significant challenge in deep learning to enable applicability in safety-critical areas such as healthcare. In this paper, we introduce Sequence Dreaming, a technique that adapts Activation Maximization to analyze sequential information, aiming to enhance the interpretability of neural networks operating on univariate time series. By leveraging this method, we visualize the temporal dynamics and patterns most influential in model decision-making processes. To counteract the generation of unrealistic or excessively noisy sequences, we enhance Sequence Dreaming with a range of regularization techniques, including exponential smoothing. This approach ensures the production of sequences that more accurately reflect the critical features identified by the neural network. Our approach is tested on a time series classification dataset encompassing applications in predictive maintenance. The results show that our proposed Sequence Dreaming approach demonstrates targeted activation maximization for different use cases so that either centered class or border activation maximization can be generated. The results underscore the versatility of Sequence Dreaming in uncovering salient temporal features learned by neural networks, thereby advancing model transparency and trustworthiness in decision-critical domains.