Neural Prophet: Bridging the Gap Between Accuracy and Interpretability

As we increase the number of auto-regressors, computational time remains constant for AR-Net while increasing quadratically for Classic AR. This figure is from the original AR-Net paper.
  1. Neural Prophet Github:
  2. R.J. Hyndman and G. Athanasopoulos. Forecasting: principles and practice
  3. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems — Volume 2, NIPS’14, pages 3104–3112, Cambridge, MA, USA, 2014. MIT Press.
  4. G. Montavon, W. Samek, and K.-R. Muller. Methods for interpreting and understanding deep neural networks. arXiv preprint arXiv:1706.07979, 2017
  5. AR-Net:
  6. Facebook Prophet:




Engineer turned Data Scientist.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Matching Niche B2B Expertise with Natural Language Processing (NLP)

Different types of Distances used in Machine Learning

NLP Model Forge

[Paper Review] 5. YOLO ver 1

Data Augmentation Programming

How to discover good data augmentation policies for ML

Example of basic data augmentation techniques

Let's make Decision Trees

The Two Paths from Natural Language Processing to Artificial Intelligence

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Alec Delany

Alec Delany

Engineer turned Data Scientist.

More from Medium

Quick guide on Deep Learning for Time-series Multi-Label Classification

Reproducing “Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks”

KerasBeats: An Easy Way to Use N-Beats in Keras

Precipitation Rainfall-runoff modelling via using a hybrid CNN-LSTM-Network