Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

KnowIt: Deep Time Series Modeling and Interpretation

M. W. Theunissen, R. Rabe, H. L. Potgieter, M. H. Davel

TL;DR

KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them that imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces.

Abstract

KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from https://must-deep-learning.github.io/KnowIt. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing new datasets, custom architectures, and the definition of different interpretability paradigms while maintaining on-the-fly modeling and interpretation of different aspects of a user's own time series data. KnowIt aims to provide an environment where users can perform knowledge discovery on their own complex time series data through building powerful deep learning models and explaining their behavior. With ongoing development, collaboration and application our goal is to make this a platform to progress this underexplored field and produce a trusted tool for deep time series modeling.

KnowIt: Deep Time Series Modeling and Interpretation

TL;DR

KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them that imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces.

Abstract

KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from https://must-deep-learning.github.io/KnowIt. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing new datasets, custom architectures, and the definition of different interpretability paradigms while maintaining on-the-fly modeling and interpretation of different aspects of a user's own time series data. KnowIt aims to provide an environment where users can perform knowledge discovery on their own complex time series data through building powerful deep learning models and explaining their behavior. With ongoing development, collaboration and application our goal is to make this a platform to progress this underexplored field and produce a trusted tool for deep time series modeling.

Paper Structure

This paper contains 20 sections, 4 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Time series modeling
  3. Problem class
  4. Regression and Classification
  5. Variable length regression
  6. Architectures
  7. Interpretability techniques
  8. Code design
  9. Operational flow
  10. General use case
  11. Data Import
  12. Model Building
  13. Interpretation
  14. Experiment output Structure
  15. Usage example
  16. ...and 5 more sections

Figures (3)

  • Figure 1: General module configuration in KnowIt. Blue elements represent code modules, purple elements represent static data structures, and pink elements represent data structures that are dynamically generated based on what is being processed.
  • Figure 2: The expected steps illustrating a complete cycle through KnowIt.
  • Figure 3: High level class interaction in KnowIt.