Sequence to sequence modeling for time series forecasting

S2S modeling using neural networks is increasingly becoming mainstream. In particular, it’s been leveraged for applications such as, but not limited to, speech recognition, language translation, and question answering. More recently, S2S has also been used for applications based on time series data. Specifically, people are actively exploring S2S modeling-based real-time anomaly detection and forecasting.

Arun Kejariwal (independent) and Ira Cohen (Anodot) provide an overview of S2S and the early use cases of S2S. They’ll walk you through how S2S modeling can be leveraged for the aforementioned use cases, visualization, real-time anomaly detection, and forecasting. You’ll learn how multilayered long short-term memory (LSTM) encodes the input time series and a deep LSTM decodes. In anomaly detection, the output is married with “traditional” statistical approaches for anomaly detection. Conceivably, any of the many variants of LSTM or recurrent neural network (RNN) alternatives of LSTM can be used to trade-off accuracy and speed. Further, given that LSTMs operate sequentially and are quite slow to train, Arun and Ira shed light on how architectures such as convolutional neural networks (CNNs) and self-attention networks (SANs) can be leveraged to achieve significant improvements in accuracy. You’ll see a concrete case study to illustrate the use of S2S for both real-time anomaly detection and forecasting for time series data.

What you'll learn

• Learn how to leverage S2S models for real-time anomaly detection and forecasting

This session is from the 2019 O'Reilly Artificial Intelligence Conference in San Jose, CA.