Publications by Sigrid Keydana

torch time series continued: A first go at multi-step prediction

We pick up where the first post in this series left us: confronting the task of multi-step time-series forecasting. Our first attempt was a workaround of sorts. The model had been trained to deliver a single prediction, corresponding to the very next point in time. Thus, if we needed a longer forecast, all we could do is use that prediction and f...

5014 sym R (9173 sym/6 pcs) 2 img

torch time series, take three: Sequence-to-sequence prediction

Today, we continue our exploration of multi-step time-series forecasting with torch. This post is the third in a series. Initially, we covered basics of recurrent neural networks (RNNs), and trained a model to predict the very next value in a sequence. We also found we could forecast quite a few steps ahead by feeding back individual predictions...

6742 sym R (7945 sym/7 pcs) 2 img

torch time series, final episode: Attention

This is the final post in a four-part introduction to time-series forecasting with torch. These posts have been the story of a quest for multiple-step prediction, and by now, we’ve seen three different approaches: forecasting in a loop, incorporating a multi-layer perceptron (MLP), and sequence-to-sequence models. Here’s a quick recap. As on...

8696 sym R (11781 sym/10 pcs) 2 img