Online continual learning through mutual information maximization
This paper proposed a new online continual learning approach called OCM based on
mutual information (MI) maximization. It achieves two objectives that are critical in dealing …
mutual information (MI) maximization. It achieves two objectives that are critical in dealing …
A theoretical study on solving continual learning
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL
settings, class incremental learning (CIL) and task incremental learning (TIL). A major …
settings, class incremental learning (CIL) and task incremental learning (TIL). A major …
A multi-head model for continual learning via out-of-distribution replay
This paper studies class incremental learning (CIL) of continual learning (CL). Many
approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most …
approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most …
Learning Equi-angular Representations for Online Continual Learning
Online continual learning suffers from an underfitted solution due to insufficient training for
prompt model updates (eg single-epoch training). To address the challenge we propose an …
prompt model updates (eg single-epoch training). To address the challenge we propose an …
A survey on out-of-distribution detection in nlp
Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of
machine learning systems in the real world. Great progress has been made over the past …
machine learning systems in the real world. Great progress has been made over the past …
Continual Evidential Deep Learning for Out-of-Distribution Detection
Uncertainty-based deep learning models have attracted a great deal of interest for their
ability to provide accurate and reliable predictions. Evidential deep learning stands out …
ability to provide accurate and reliable predictions. Evidential deep learning stands out …
Open-world continual learning: Unifying novelty detection and continual learning
As AI agents are increasingly used in the real open world with unknowns or novelties, they
need the ability to (1) recognize objects that (i) they have learned and (ii) detect items that …
need the ability to (1) recognize objects that (i) they have learned and (ii) detect items that …
Hierarchical task-incremental learning with feature-space initialization inspired by neural collapse
Incremental learning models need to update the categories and their conceptual
understanding over time. The current research has placed more emphasis on learning new …
understanding over time. The current research has placed more emphasis on learning new …
Prediction error-based classification for class-incremental learning
Class-incremental learning (CIL) is a particularly challenging variant of continual learning,
where the goal is to learn to discriminate between all classes presented in an incremental …
where the goal is to learn to discriminate between all classes presented in an incremental …
Open-World Continual Learning: A Framework
S Mazumder, B Liu - Lifelong and Continual Learning Dialogue Systems, 2024 - Springer
As more and more AI agents are used in practice, we need to think about how to make these
agents fully autonomous so that they can (1) learn by themselves continually in a self …
agents fully autonomous so that they can (1) learn by themselves continually in a self …