Results 11 to 20 of about 3,000 (250)
Remembering for the right reasons: Explanations reduce catastrophic forgetting
Applied AI Letters, 2021 The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance degradation on ...
Sayna Ebrahimi
exaly +2 more sources
SD-IDD: Selective Distillation for Incremental Defect Detection [PDF]
SensorsSurface defects in industrial production are complex and diverse. Therefore, deep learning-based defect detection models must consistently adapt to newly emerging defect categories. The trained models generally suffer from catastrophic forgetting as they
Jing Li +3 more
doaj +2 more sources
Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization [PDF]
Proceedings of the National Academy of Sciences of the United States of America, 2018 David Freedman +2 more
exaly +2 more sources
Do not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting [PDF]
2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021 One of the major limitations of deep learning models is that they face catastrophic forgetting in an incremental learning scenario. There have been several approaches proposed to tackle the problem of incremental learning. Most of these methods are based on knowledge distillation and do not adequately utilize the information provided by older task ...
Vinod K. Kurmi +3 more
openaire +2 more sources
Variational Continuous Bayesian Meta-learning Based Algorithm for Recommendation [PDF]
Jisuanji kexue, 2023 Meta-learning methods have been introduced into recommendation algorithms in recent years to alleviate the problem of cold start.The existing meta-learning algorithms can only improve the ability of the algorithm to deal with a set of statically ...
ZHU Wentao, LIU Wei, LIANG Shangsong, ZHU Huaijie, YIN Jian
doaj +1 more source
Incremental Fault Diagnosis Method Based on Metric Feature Distillation and Improved Sample Memory
IEEE Access, 2023 Incremental learning-based fault diagnosis systems (IFD) are widely used because of their ability to handle constantly updated fault data and types. However, the catastrophic forgetting problem remains the most crucial contemporary challenge facing IFD ...
Qilang Min +3 more
doaj +1 more source
On Sequential Bayesian Inference for Continual Learning
Entropy, 2023 Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks.
Samuel Kessler +4 more
doaj +1 more source
Catastrophic Forgetting in the Context of Model Updates
CoRR, 2023 A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline, you can train a new model from scratch (randomly initialized weights) on all existing data.
Richard E. Harang, Hillary Sanders
openaire +2 more sources
Incremental Learning for Online Data Using QR Factorization on Convolutional Neural Networks
Sensors, 2023 Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the
Jonghong Kim +4 more
doaj +1 more source
Combating catastrophic forgetting with developmental compression [PDF]
Proceedings of the Genetic and Evolutionary Computation Conference, 2018 Generally intelligent agents exhibit successful behavior across problems in several settings. Endemic in approaches to realize such intelligence in machines is catastrophic forgetting: sequential learning corrupts knowledge obtained earlier in the sequence, or tasks antagonistically compete for system resources.
Shawn L. E. Beaulieu +2 more
openaire +2 more sources