A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning

TL;DR

This paper reviews the opportunities and challenges of applying deep learning to online, streaming, and continuous learning environments, emphasizing the use of frameworks like River and Deep-River.

Contribution

It provides a retrospective overview of online deep learning, highlighting potential pitfalls and opportunities based on a tutorial presented at ECML PKDD 2023.

Findings

Deep learning has limited application in online, streaming, and continuous learning.

Frameworks like River and Deep-River facilitate online deep learning.

Challenges include adapting neural networks to changing data streams.

Abstract

Machine learning algorithms have become indispensable in today's world. They support and accelerate the way we make decisions based on the data at hand. This acceleration means that data structures that were valid at one moment could no longer be valid in the future. With these changing data structures, it is necessary to adapt machine learning (ML) systems incrementally to the new data. This is done with the use of online learning or continuous ML technologies. While deep learning technologies have shown exceptional performance on predefined datasets, they have not been widely applied to online, streaming, and continuous learning. In this retrospective of our tutorial titled Opportunities and Challenges of Online Deep Learning held at ECML PKDD 2023, we provide a brief overview of the opportunities but also the potential pitfalls for the application of neural networks in online learning environments using the frameworks River and Deep-River.