Results 71 to 80 of about 7,740,063 (200)

Neuromodulated Meta-Learning

CoRR
Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks.
Jingyao Wang, Huijie Guo, Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Hui Xiong 0001, Gang Hua 0001   +6 more
openaire   +3 more sources

Large margin meta-learning for few-shot classification [PDF]

, 2018
This paper proposes a large margin principle to overcome the problem of data scarcity in training meta-learning models for few-shot classification. To realize it, we develop an efficient framework that can be easily incorporated in existing metric-based ...
Wang, Y, Xiang, W, Li, VOK, Gu, J, Zhang, L, Wu, XM, Li, Q   +6 more
core  

Meta-learning algorithms and applications [PDF]

Meta-learning in the broader context concerns how an agent learns about their own learning, allowing them to improve their learning process. Learning how to learn is not only beneficial for humans, but it has also shown vast benefits for improving how ...
Bohdal, Ondrej
core   +1 more source

Rare disease classification via difficulty-aware meta learning

, 2022
Deep convolutional neural networks (ConvNets) have achieved state-of-the-art performance in various medical image analysis tasks. The success is partially attributed to a large amount of labeled data.
Yu, L, Fu, C, Xing, L, Heng, Pheng Ann, Heng, P, Li, Xiaomeng, Yu, Lequan, Jin, Y, Li, X, Jin, Yueming, Fu, Chi Wing, Xing, Lei   +11 more
core   +1 more source

Subspace Learning for Effective Meta-Learning

, 2022
Meta-learning aims to extract meta-knowledge from historical tasks to accelerate learning on new tasks. Typical meta-learning algorithms like MAML learn a globally-shared meta-model for all tasks.
Kwok, James T., Zhang, Yu, Jiang, Weisen
core  

Skill-based Meta-Reinforcement Learning

, 2022
While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible.
Nam, Taewook, Lim, Joseph Jaewhan, Sun, Shao-Hua, Pertsch, Karl, Hwang, Sung Ju   +4 more
core  

Meta Lifelong-Learning With Selective and Task-Aware Adaptation

IEEE Access
Meta-learning has been applied to lifelong language learning due to its ability to find an optimal model for efficient adaptation to any learned tasks.
Thanapapas Horsuwan, Piyawat Lertvittayakumjorn, Kasidis Kanwatchara, Boonserm Kijsirikul, Peerapon Vateekul   +4 more
doaj   +1 more source

Catecholaminergic modulation of meta-learning [PDF]

eLife, 2019
The remarkable expedience of human learning is thought to be underpinned by meta-learning, whereby slow accumulative learning processes are rapidly adjusted to the current learning environment. To date, the neurobiological implementation of meta-learning remains unclear.
Cook, J.L., Swart, J.C., Froböse, M.I., Diaconescu, A.O., Geurts, D.E.M., den Ouden, H.E.M., den Ouden, H.E.M., Cools, R., Cools, R.   +8 more
openaire   +5 more sources

Graphical Knowledge Representation Tools for High Quality Learning

Envigogika, 2019
The common aim of graphical knowledge representation techniques in education is to promote a deep approach to learning. There is empirical evidence that the use of graphical knowledge representation tools enhances learning and improves knowledge – when ...
Salim Lardjane
doaj  

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

AI
Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples.
Jie Ren, Changmiao Li, Yaohui An, Weichuan Zhang, Changming Sun   +4 more
doaj   +1 more source