⏳ Edge#55: DeepAR, multi-dimensional time-series forecasting, and Sktime
TheSequence is the best way to build and reinforce your knowledge about machine learning and AI
You’re on the free list for the Sunday news digest TheSequence Scope. We sent you TheSequence Edge so you can keep up with the topics we cover. For the full experience, become a Premium subscriber. Because it helps you stay up-to-date with the important developments in the AI world and saves you a lot of time.
Check the Quiz below: Participate to win the Premium subscription for 6 months!
💡 ML Concept of the Day: What is DeepAR?
Continuing our series about time-series forecasting (Edge#49, Edge#51, Edge#53), we would like to cover one of the models that has become increasingly popular since its first release. We are talking about DeepAR, part of a new generation of models that are trying to apply deep neural networks to time-series forecasting scenarios. Specifically, DeepAR leverages recurrent neural networks (RNNs) for solving large scale time-series problems.
Large-scale seems like an overloaded term when it comes to time-series analysis. In the case of DeepAR, the model focuses on a specific type of scaling challenge related to problems that include a disproportionately large number of time-series ->let me explain
🔎 ML Research You Should Know: DeepGLO is a Time-Series Model for High-Dimensional Time-Series Forecasting
In its Amazon Research proposes DeepGLO, a deep forecasting method that can combine multiple dimensions to make a prediction.
Why is it so important: Multi-dimensional time-series forecasting problems are incredibly common across many industries and they are very difficult to solve ->let's dive deeper
🤖 ML Technology to Follow: sktime is a Unified Time Series Framework for Scikit-Learn
Initially incubated by the UK Economic and Social Research Council, the Consumer Data Research Centre, and The Alan Turing Institute, sktime can be seen as a unified framework for building time-series forecasting solutions in scikit-learn ->why should you know about this and how you can use it
🧠 The Quiz
Now, to our regular quiz. After ten quizzes, we will reward the winners. The questions are the following:
What is a traditional time-series forecasting scenario for using a DeepAR algorithm?
What is the main value proposition of the sktime framework?
That was fun! Thank you. See you on Thursday 😉
TheSequence is a summary of groundbreaking ML research papers, engaging explanations of ML concepts, and exploration of new ML frameworks and platforms. TheSequence keeps you up to date with the news, trends, and technology developments in the AI field.
5 minutes of your time, 3 times a week – you will steadily become knowledgeable about everything happening in the AI space.
