.png){kind=icon}
返回
Logarithmic Continual Learning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3218907.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in subsequent tasks, and the trained model can access only a current task. Contemporary CL methods employ generative models to replay previous samples and train them recursively with a combination of current and regenerated past data. This recurrence leads to superfluous computations as the same past samples are regenerated after each task, and the reconstruction quality successively degrades. In this work, we address these limitations and propose a new generative rehearsal architecture that requires, at most, a logarithmic number of retraining sessions for each sample. Our approach leverages the allocation of past data in a set of generative models such that most of them do not require retraining after a task. The experimental evaluation of our logarithmic continual learning approach shows the superiority of our method with respect to the state-of-the-art generative rehearsal methods.
Keyword:
Deep learning
Data models
Memory management
Computational modeling
Learning systems
Image reconstruction
Adaptation models
Continual learning
deep learning
incremental learning
rehearsal methods
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Arterielle Ex-situ-Nachperfusion unter Druck zur Vermeidung von "Ischemic Type Biliary Lesions" nach orthotoper Lebertransplantation在正位肝移植后，为避免“缺血型胆道病变”，进行加压下的动脉体外后灌注。.png)
Der Chirurg
Der ChirurgIF0
PREAI
分享收藏Human-level concept learning through probabilistic program induction通过概率程序归纳进行人类水平的概念学习SCIENCE
OAAI
SCIENCEIF45.8
OAAI分享收藏The Homeoprotein Nanog Is Required for Maintenance of Pluripotency in Mouse Epiblast and ES CellsCellOAAI
CellIF0
OAAI分享收藏
查看更多内容