Meta-Learning for Time Series Forecasting (DeepTime) in PyTorch Lightning

Reza Yazdanfar
Towards AI
Published in
4 min readJan 20, 2023

This article is devoted to describing a new type of deep learning model to cope with the usual problems in time series (covariate shift and conditional distribution shift)-come from being non-stationary-by using meta-learning formulation to forecast the future. The model is named DeepTime, which is a deep time-index model combined with using meta-learning. This model is a great example of the model’s synergies with a meta-learning formulation for time series forecasting.

I am building nouswise🤗!! check it out and get on the waitlist😉 If you want early access hit me up on X (Twitter). Let me know your thoughts.

DeepTime in one Figure

Figure 1. Deep Time-index Model Architecture. [source]

In General, you can see there are three types of layers in DeepTime:

  1. Ridge Regressor
  2. Multi-layer Perceptron (MLP)
  3. Random Fourier Features

Let’s see what these are layer doing:

1. Ridge Regressor

2. MLP (multi-layer perceptron)

Well, nothing new!! These are the linear regression formula that we use in simple (and, of…

Published in Towards AI

The leading AI community and content platform focused on making AI accessible to all. Check out our new course platform: https://academy.towardsai.net/courses/beginner-to-advanced-llm-dev

Responses (3)