Results 31 to 40 of about 24,131 (257)

Survey of Pre-training-based Continual Learning Methods (Invited) [PDF]

Jisuanji gongcheng
Traditional machine learning algorithms perform well only when the training and testing sets are identically distributed. They cannot perform incremental learning for new categories or tasks that were not present in the original training set.
LU Yue, ZHOU Xiangyu, ZHANG Shizhou, LIANG Guoqiang, XING Yinghui, CHENG De, ZHANG Yanning
doaj   +1 more source

Homeostasis-Inspired Continual Learning: Learning to Control Structural Regularization

IEEE Access, 2021
Learning continually without forgetting might be one of the ultimate goals for building artificial intelligence (AI). However, unless there are enough resources equipped, forgetting knowledge acquired in the past is inevitable.
Joonyoung Kim, Hyowoon Seo, Wan Choi, Kyomin Jung   +3 more
doaj   +1 more source

Decentralized Federated Continual Learning Method Combined with Meta-learning [PDF]

Jisuanji kexue
For the problems of continual learning and data security in federated continual scenarios,a decentralized federated continual learning framework combined with meta-learning is constructed.First,in order to solve the problem of catastrophic forgetting in ...
HUANG Nan, LI Dongdong, YAO Jia, WANG Zhe
doaj   +1 more source

Kernel Continual Learning

CoRR, 2021
This paper introduces kernel continual learning, a simple but effective variant of continual learning that leverages the non-parametric nature of kernel methods to tackle catastrophic forgetting. We deploy an episodic memory unit that stores a subset of samples for each task to learn task-specific classifiers based on kernel ridge regression. This does
Derakhshani, M.M., Zhen, X., Shao, L., Snoek, C.G.M.   +3 more
openaire   +4 more sources

Continuous Invariance Learning

CoRR, 2023
Invariance learning methods aim to learn invariant features in the hope that they generalize under distributional shifts. Although many tasks are naturally characterized by continuous domains, current invariance learning techniques generally assume categorically indexed domains. For example, auto-scaling in cloud computing often needs a CPU utilization
Yong Lin, Fan Zhou 0012, Lu Tan, Lintao Ma, Jiameng Liu, Yansu He, Yuan Yuan, Yu Liu 0071, James Zhang, Yujiu Yang 0001, Hao Wang 0014   +10 more
openaire   +3 more sources

Continual learning with hypernetworks

CoRR, 2019
Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of
von Oswald, Johannes, Henning, Christian, Grewe, Benjamin F, Sacramento, João   +3 more
openaire   +5 more sources

Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks

IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2019
Continual learning is the ability to acquire a new task or knowledge without losing any previously collected information. Achieving continual learning in artificial intelligence (AI) is currently prevented by catastrophic forgetting, where training of a ...
Irene Munoz-Martin, Stefano Bianchi, Giacomo Pedretti, Octavian Melnic, Stefano Ambrogio, Daniele Ielmini   +5 more
doaj   +1 more source

Metrics and Continuity in Reinforcement Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2021
In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage {\em state similarity} (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples.
Charline Le Lan, Marc G. Bellemare, Pablo Samuel Castro   +2 more
openaire   +2 more sources

Bilevel Continual Learning

CoRR, 2020
Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well on the previous tasks.
Quang Pham, Doyen Sahoo, Chenghao Liu, Steven C. H. Hoi   +3 more
openaire   +2 more sources

Continual Object Learning

, 2021
This work focuses on building frameworks to strengthen the relation between human and machine learning. This is achieved by proposing a new category of algorithms and a new theory to formalize the perception and categorization of objects. For what concerns the algorithmic part, we developed a series of procedures to perform Interactive Continuous Open ...
openaire   +1 more source