On the role of neurogenesis in overcoming catastrophic forgetting
원문 초록
Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform static networks in incremental learning scenarios, even when bounded by the same amount of memory in both cases. Learning is unsupervised in our models, a condition that additionally makes training more challenging whilst increasing the realism of the study, since humans are able to learn without dense manual annotation. Our results on artificial neural networks reinforce that structural plasticity constitutes effective prevention against catastrophic forgetting in non-stationary environments, as well as empirically supporting the importance of neurogenesis in the mammalian brain.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Privacy-Aware Lifelong Learning
Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context Adaptation
Lifelong Learning of Large Language Model based Agents: A Roadmap
Lifelong Whole Slide Image Analysis: Online Vision-Language Adaptation and Past-to-Present Gradient Distillation
Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning
Generate to Discriminate: Expert Routing for Continual Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.