Incremental on-line learning: A review and comparison of state of the art algorithms

By Viktor Losing, Barbara Hammer, Heiko Wersing. 2018

353 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research, Meta & Continual Learning, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Meta & Continual Learning

In Statistical Learning Theory

Citations in the corpus

Online Continual Learning with Contrastive Vision Transformer (2022, background): “This paper focuses on a more realistic and challenging setting: online continual learning (online CL) [34,50,67], where the model learns a sequence of classification tasks with a single pass over the data and without task boundaries.”
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (2021, methodology): “Despite being more realistic (Losing et al., 2018; He et al., 2020), online CL have not been popular (Prabhu et al., 2020) due to the difﬁculty and subtle differences in the setups in the literature.”
Ternary Feature Masks: continual learning without any forgetting (2020, methodology): “Finally, we want to mention that there have been some methods proposed that consider a memory budget [13], or an online setup [31], and methods with exemplars where each sample is used only once [12, 14, 15].”
Class Boundary Exemplar Selection Based Incremental Learning for Automatic Target Recognition (2020, methodology): “Recently, incremental learning gained more attention especially in learning from data streams, and many deﬁnitions of incremental learning are introduced in the literature [7], [19], [23], [28].”
Towards the Deployment of Machine Learning Solutions in Network Traffic Classification: A Systematic Survey (2019, methodology): “There are more advanced techniques such as, incremental learning that aims at updating in an online manner the ML models with new incoming inputs [39].”