Zobrazeno 1 - 10
of 396
pro vyhledávání: '"Loo Chu Kiong"'
In federated learning, data heterogeneity significantly impacts performance. A typical solution involves segregating these parameters into shared and personalized components, a concept also relevant in multi-task learning. Addressing this, we propose
Externí odkaz:
http://arxiv.org/abs/2403.14371
Autor:
Masuyama, Naoki, Nojima, Yusuke, Toda, Yuichiro, Loo, Chu Kiong, Ishibuchi, Hisao, Kubota, Naoyuki
Publikováno v:
IEEE Access, vol. 12, pp. 139692-139710, September 2024
With the increasing importance of data privacy protection, various privacy-preserving machine learning methods have been proposed. In the clustering domain, various algorithms with a federated learning framework (i.e., federated clustering) have been
Externí odkaz:
http://arxiv.org/abs/2309.03487
Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. Such devices have limited processing and memory storage capabilities, whereas continual learning acquires data over a long period of
Externí odkaz:
http://arxiv.org/abs/2306.13410
Autor:
Masuyama, Naoki, Takebayashi, Takanori, Nojima, Yusuke, Loo, Chu Kiong, Ishibuchi, Hisao, Wermter, Stefan
In general, a similarity threshold (i.e., a vigilance parameter) for a node learning process in Adaptive Resonance Theory (ART)-based algorithms has a significant impact on clustering performance. In addition, an edge deletion threshold in a topologi
Externí odkaz:
http://arxiv.org/abs/2305.01507
Convolutional neural networks (CNNs) apply well with food image recognition due to the ability to learn discriminative visual features. Nevertheless, recognizing distorted images is challenging for existing CNNs. Hence, the study modelled a generaliz
Externí odkaz:
http://arxiv.org/abs/2206.05853
Publikováno v:
In Applied Soft Computing November 2024 165
Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for learning
Externí odkaz:
http://arxiv.org/abs/2111.08458