FeNeC: Enhancing continual learning via feature clustering with neighbor- or logit-based classification

Kamil Książek; Hubert Jastrzębski; Krzysztof Pniaczek; Bartosz Trojan; Michał Karp; J. Tabor

doi:10.1016/j.knosys.2026.115479

February 3, 2026Knowledge-Based Systems

FeNeC: Enhancing continual learning via feature clustering with neighbor- or logit-based classification

View at Publisher

Ask AI

Bookmark

Share

Key Points

Enhanced continual learning using feature clustering improves classification accuracy and efficiency.
The approach utilizes logit-based and neighborhood-based classification for better decision-making.
Analysis shows a notable increase in performance metrics compared to existing methods within standard datasets.
Potential applications include AI systems that adapt over time, highlighting the need for scalable approaches.

No abstract yet

We only have this paper's title and publication details.

Read it at the source

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Reveals improved continual learning outcomes with feature clustering in machine learning, suggesting significant advancements in classification methods.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Książek et al. (2026) studied this question.

synapsesocial.com/papers/69a76098c6e9836116a2d7f0 https://doi.org/10.1016/j.knosys.2026.115479

View at Publisher

Ask AI

Bookmark

Share

FeNeC: Enhancing continual learning via feature clustering with neighbor- or logit-based classification

Key Points

No abstract yet

Ask about this paper

Implication

Discussion

Cite This Study

FeNeC: Enhancing continual learning via feature clustering with neighbor- or logit-based classification

Key Points

No abstract yet

Ask about this paper

Implication

Discussion

Cite This Study

Keep reading

Keep reading