Presented By
O’Reilly + Cloudera
Make Data Work
March 25-28, 2019
San Francisco, CA

Dilated neural networks for time series forecasting

Chenhui Hu (Microsoft)
2:40pm3:20pm Wednesday, March 27, 2019
Average rating: ****.
(4.67, 6 ratings)

Who is this presentation for?

  • Data scientists

Level

Intermediate

Prerequisite knowledge

  • A basic understanding of deep learning and time series forecasting

What you'll learn

  • Explore dilated neural networks (including dilated CNNs and dilated RNNs)
  • Understand the design principles and the advantages of dilated neural networks over other neural network methods
  • Learn how to implement such networks and apply them to solve time series forecasting problems

Description

Recently, deep neural networks (DNNs) have been used with great success to solve time series forecasting problems such as web traffic forecasts, product sales forecasts, and financial time series forecasts. The ability to capture long-range and nonlinear data dependencies is the key reason why deep learning methods can achieve better forecast accuracy than traditional machine learning approaches. However, DNNs need more time and data to train.

Chenhui Hu offers an overview of dilated neural networks—a class of DNNs in the frontier of deep learning research that tackle the above challenges—and demonstrates their advantages with real use cases. This class of networks includes both dilated convolutional neural networks (dilated CNNs) and dilated recurrent neural networks (dilated RNNs). Based on dilated connections, dilated neural networks can capture data dependencies in a large spatial or temporal range while only requiring that the number of parameters grow logarithmically. As a result, they are more efficient to train when compared with the current state-of-the-art DNN models such as long short-term memory (LSTM) models.

Chenhui demonstrates the advantages of dilated neural networks in terms of training efficiency and forecast accuracy by applying them to solve sales forecasting and financial time series forecasting problems and shows that they can obtain at least as good or better accuracy on such nonlinear, noisy forecasting tasks.

Source code for the implementations will be available in GitHub.

Photo of Chenhui Hu

Chenhui Hu

Microsoft

Chenhui Hu is a data scientist in the Cloud and AI Division at Microsoft. His current interests include retail forecast, inventory optimization, IoT data, and deep learning. He also has research experience in wireless networks and network data analysis. He’s a recipient of the third IEEE ComSoc Asia-Pacific Outstanding Paper Award. He holds a PhD from Harvard University, where his PhD thesis focused on biomedical imaging data mining.