Results 41 to 50 of about 339,627 (329)
Catastrophic Forgetting Problem in Semi-Supervised Semantic Segmentation
IEEE Access, 2022 Restricted by the cost of generating labels for training, semi-supervised methods have been applied to semantic segmentation tasks and have achieved varying degrees of success. Recently, the semi-supervised learning method has taken pseudo supervision as
Yan Zhou +4 more
doaj +1 more source
A divided and prioritized experience replay approach for streaming regression
MethodsX, 2021 In the streaming learning setting, an agent is presented with a data stream on which to learn from in an online fashion. A common problem is catastrophic forgetting of old knowledge due to updates to the model.
Mikkel Leite Arnø +2 more
doaj +1 more source
GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting [PDF]
Computer Vision and Pattern Recognition, 2023 Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community. However, catastrophic forgetting caused by data heterogeneity and partial participation poses distinctive ...
Kangyang Luo +3 more
semanticscholar +1 more source
Pseudorehearsal in actor-critic agents with neural network function approximation [PDF]
, 2018 Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation.
Marochko, Vladimir +3 more
core +9 more sources
CL3: Generalization of Contrastive Loss for Lifelong Learning
Journal of Imaging, 2023 Lifelong learning portrays learning gradually in nonstationary environments and emulates the process of human learning, which is efficient, robust, and able to learn new concepts incrementally from sequential experience.
Kaushik Roy +3 more
doaj +1 more source
Overcoming Catastrophic Forgetting via Direction-Constrained Optimization
, 2023 This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification network in a continual learning framework. The training data is non-stationary and the non-stationarity is imposed by a sequence of distinct tasks.
Teng, Yunfei +5 more
openaire +2 more sources
IEEE Access, 2023 Continual learning aims to enable neural networks to learn new tasks without catastrophic forgetting of previously learned knowledge. Orthogonal Gradient Descent algorithms have been proposed as an effective solution to mitigate catastrophic forgetting ...
Da Eun Lee +3 more
doaj +1 more source
Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time.
Genta Indra Winata +7 more
semanticscholar +1 more source
Understanding Catastrophic Forgetting in Language Models via Implicit Inference [PDF]
International Conference on Learning Representations, 2023 We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outside the narrow fine-tuning distribution.
Suhas Kotha +2 more
semanticscholar +1 more source
Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection [PDF]
International Conference on Machine Learning, 2023 Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset.
Xiaohui Zhang +4 more
semanticscholar +1 more source