[1911.12436] AR-Net: A simple Auto-Regressive Neural Network for time-series

In this paper we present a new framework for time-series modeling that combines the best of traditional statistical models and neural networks. We focus on time-series with long-range dependencies, needed for monitoring fine granularity data (e.g. minutes, seconds, milliseconds), prevalent in operational use-cases. Traditional models, such as auto-regression fitted with least squares (Classic-AR) can model time-series with a concise and interpretable model. When dealing with long-range dependencies, Classic-AR models can become intractably slow to fit for large data. Recently, sequence-to-sequence models, such as Recurrent Neural Networks, which were originally intended for natural language processing, have become popular for time-series. However, they can be overly complex for typical time-series data and lack interpretability. A scalable and interpretable model is needed to bridge the statistical and deep learning-based approaches. As a first step towards this goal, we propose mo

3 mentions: @unsorsodicorda@meta_takoroy@CarlRioux
Date: 2019/12/03 09:50

Referring Tweets

@unsorsodicorda Interesting work by @facebookai on interpretable and scalable autoregressive models for time series based on feedforward neural networks. Sometimes simplicity is all you need 🙂 t.co/8MVkbKuglM
@meta_takoroy 伝統的なARモデルと同様の解釈可能性をもたせつつ、長期の依存関係もモデル化できるようにする、深層学習モデルの検討。FacebookとStanford。 / t.co/Ixdz0lGmZ8

Bookmark Comments

Related Entries

Read more [1707.06873] Semantic Image Synthesis via Adversarial Learningcontact arXivarXiv Twitter
0 users, 1 mentions 2020/01/17 06:51
Read more Turn GPUs to Heaters: An Energy-efficient Model to Train Neural Networks - Max Welling @NeurIPS 2019...
0 users, 1 mentions 2020/01/17 08:21
Read more GitHub - econti/faucetml
0 users, 1 mentions 2020/01/22 02:21
Read more OpenML
0 users, 1 mentions 2020/01/28 20:20
Read more Using Video Conferencing for Distance Learning | BlueJeans Blog
0 users, 1 mentions 2020/01/30 20:22