# Explaining Deep Classification of Time-Series Data with Learned Prototypes

arXiv: https://arxiv.org/abs/1904.08935 · HTML: https://mlsanity.com/paper/1904.08935/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 30 of 30)

- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (2021)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks](https://mlsanity.com/paper/2105.02968/) (2021)
- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations](https://mlsanity.com/paper/2308.08162/) (2023)
- [ICICLE: Interpretable Class Incremental Continual Learning](https://mlsanity.com/paper/2303.07811/) (2023)
- [LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision](https://mlsanity.com/paper/2405.14331/) (2024)
- [Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning](https://mlsanity.com/paper/2211.05207/) (2022)
- [A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions](https://mlsanity.com/paper/2204.12822/) (2022)
- [XAI Methods for Neural Time Series Classification: A Brief Review](https://mlsanity.com/paper/2108.08009/) (2021)
- [Multi-Stage Prototype Learning for Interpretable Time Series Classification](https://mlsanity.com/paper/2106.09636/) (2021)
- [ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging](https://mlsanity.com/paper/2309.16353/) (2023)
- [Prototypes as Explanation for Time Series Anomaly Detection](https://mlsanity.com/paper/2307.01601/) (2023)
- [Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation](https://mlsanity.com/paper/2409.09497/) (2024)
- [SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence](https://mlsanity.com/paper/2507.19321/) (2025)
- [From Confusion to Clarity: ProtoScore -- A Framework for Evaluating Prototype-Based XAI](https://mlsanity.com/paper/2511.08361/) (2025)
- [PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification](https://mlsanity.com/paper/2102.05917/) (2021)
- [Towards Explainable Artificial Intelligence in Banking and Financial Services](https://mlsanity.com/paper/2112.08441/) (2021)
- [Intermediate Entity-based Sparse Interpretable Representation Learning](https://mlsanity.com/paper/2212.01641/) (2022)
- [Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion](https://mlsanity.com/paper/2306.13410/) (2023)
- [Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification](https://mlsanity.com/paper/2408.12666/) (2024)
- [ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts](https://mlsanity.com/paper/2511.02152/) (2025)
- [SigTime: Learning and Visually Explaining Time Series Signatures](https://mlsanity.com/paper/2512.12076/) (2025)
- [Local Explanations for Clinical Search Engine results](https://mlsanity.com/paper/2110.12891/) (2021)
- [Evaluating Simplification Algorithms for Interpretability of Time Series Classification](https://mlsanity.com/paper/2505.08846/) (2025)
- [CanadaFireSat: Toward high-resolution wildfire forecasting with multiple modalities](https://mlsanity.com/paper/2506.08690/) (2025)
- [When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate](https://mlsanity.com/paper/2512.03578/) (2025)
- [Interpretability in Deep Time Series Models Demands Semantic Alignment](https://mlsanity.com/paper/2602.02239/) (2026)
- [INSIGHTS: Demonstration-Based Summaries of Time Series Predictors](https://mlsanity.com/paper/2605.18849/) (2026)

## Abstract (arXiv)

The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning models to learn stereotypical representations or "prototypes" during training to elucidate the algorithmic decision-making process. We study how leveraging prototypes effect classification decisions of two dimensional time-series data in a few different settings: (1) electrocardiogram (ECG) waveforms to detect clinical bradycardia, a slowing of heart rate, in preterm infants, (2) respiration waveforms to detect apnea of prematurity, and (3) audio waveforms to classify spoken digits. We improve upon existing models by optimizing for increased prototype diversity and robustness, visualize how these prototypes in the latent space are used by the model to distinguish classes, and show that prototypes are capable of learning features on two dimensional time-series data to produce explainable insights during classification tasks. We show that the prototypes are capable of learning real-world features - bradycardia in ECG, apnea in respiration, and articulation in speech - as well as features within sub-classes. Our novel work leverages learned prototypical framework on two dimensional time-series data to produce explainable insights during classification tasks.