# Visualising Deep Network's Time-Series Representations

arXiv: https://arxiv.org/abs/2103.07176 · HTML: https://mlsanity.com/paper/2103.07176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods](https://mlsanity.com/paper/1705.03233/) (2017)
- [Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis](https://mlsanity.com/paper/1712.00975/) (2017)
- [Highly comparative feature-based time-series classification](https://mlsanity.com/paper/1401.3531/) (2014)
- [Highly comparative time-series analysis: The empirical structure of time series and their methods](https://mlsanity.com/paper/1304.1209/) (2013)
- [Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data](https://mlsanity.com/paper/1809.07861/) (2018)
- [m-TSNE: A Framework for Visualizing High-Dimensional Multivariate Time Series](https://mlsanity.com/paper/1708.07942/) (2017)

## Abstract (arXiv)

Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model. There exist a few methods that allow to visualise and explain why a model has made a certain prediction. Those methods, however, allow visualisation of the link between the input and output of the model without presenting how the model learns to represent the data used to train the model as whole. In this paper, a method that addresses that issue is proposed, with a focus on visualising multi-dimensional time-series data. Experiments on a high-frequency stock market dataset show that the method provides fast and discernible visualisations. Large datasets can be visualised quickly and on one plot, which makes it easy for a user to compare the learned representations of the data. The developed method successfully combines known techniques to provide an insight into the inner workings of time-series classification models.