Results 31 to 40 of about 252,836 (257)
Generalization of Forgery Detection With Meta Deepfake Detection Model
IEEE Access, 2023 Face forgery generating algorithms that produce a range of manipulated videos/images have developed quickly. Consequently, this causes an increase in the production of fake information, making it difficult to identify.
Van-Nhan Tran +4 more
doaj +1 more source
, 2019 Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible.
openaire +2 more sources
Learning with few samples in deep learning for image classification, a mini-review
Frontiers in Computational Neuroscience, 2023 Deep learning has achieved enormous success in various computer tasks. The excellent performance depends heavily on adequate training datasets, however, it is difficult to obtain abundant samples in practical applications.
Rujun Zhang, Qifan Liu
doaj +1 more source
Meta Learning for Causal Direction
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 The inaccessibility of controlled randomized trials due to inherent constraints in many fields of science has been a fundamental issue in causal inference. In this paper, we focus on distinguishing the cause from effect in the bivariate setting under limited observational data.
Ton, J-F, Sejdinovic, D, Fukumizu, K
openaire +3 more sources
, 2013 In: Encyclopedia of Systems Biology, W. Dubitzky, O. Wolkenhauer, K-H Cho, H.
+5 more sources
A Meta Learning-Based Approach for Zero-Shot Co-Training
IEEE Access, 2021 The lack of labeled data is one of the main obstacles to the application of machine learning algorithms in a variety of domains. Semi-supervised learning, where additional samples are automatically labeled, is a common and cost-effective approach to ...
Guy Zaks, Gilad Katz
doaj +1 more source
Deep Neural Network for Emotion Recognition Based on Meta-Transfer Learning
IEEE Access, 2022 In recent years, many EEG-based emotion recognition methods have been proposed, which can achieve good performance on single-subject data. However, when the models are applied to cross-subject scenarios, due to the existence of subject differences, these
Hengyao Tang +2 more
doaj +1 more source
When and why does motor preparation arise in recurrent neural network models of motor control?
eLifeDuring delayed ballistic reaches, motor areas consistently display movement-specific activity patterns prior to movement onset. It is unclear why these patterns arise: while they have been proposed to seed an initial neural state from which the movement ...
Marine Schimel +2 more
doaj +1 more source
ROA: A Rapid Learning Scheme for In-Situ Memristor Networks
Frontiers in Artificial Intelligence, 2021 Memristors show great promise in neuromorphic computing owing to their high-density integration, fast computing and low-energy consumption. However, the non-ideal update of synaptic weight in memristor devices, including nonlinearity, asymmetry and ...
Wenli Zhang +4 more
doaj +1 more source
In search of the neural circuits of intrinsic motivation
Frontiers in Neuroscience, 2007 Children seem to acquire new know-how in a continuous and open-ended manner. In this paper, we hypothesize that an intrinsic motivation to progress in learning is at the origins of the remarkable structure of children's developmental trajectories.
Frederic Kaplan, Pierre-Yves Oudeyer
doaj +1 more source