Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Sibo Gai"'
Publikováno v:
Entropy, Vol 26, Iss 1, p 93 (2024)
The ability to learn continuously is crucial for a robot to achieve a high level of intelligence and autonomy. In this paper, we consider continual reinforcement learning (RL) for quadruped robots, which includes the ability to continuously learn sub
Externí odkaz:
https://doaj.org/article/43c40916c5a64dc78975e264bd3365fa
Publikováno v:
IJCNN
Recently, meta learning methods able to provide multiple initializations have drawn much attention due to its capability of handling multi-modal tasks. However, the modal differences in multi-modal distributions aggravate the catastrophic forgetting.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7906b4f383a75d55896c3b1084b0d7cc
https://doi.org/10.1109/ijcnn52387.2021.9533797
https://doi.org/10.1109/ijcnn52387.2021.9533797
Publikováno v:
IEEE BigData
Matrix factorization is one of the most successful methods for single-criterion recommender systems but not for multi-criteria recommender systems that contain multiple criterion-specific ratings. Tensor factorization methods have been developed to l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4dd4d13fd4de2a4b2615d964a4b9caad
https://doi.org/10.1109/bigdata47090.2019.9005677
https://doi.org/10.1109/bigdata47090.2019.9005677
Publikováno v:
ICDM Workshops
Collaborative filtering (CF) faces two challenges for recommendations: data sparsity and cold-start issue. One solution is to incorporate the side information and the other is to utilize relevant knowledge. In this paper, a cross-domain deep collabor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d0f63a61af4ab7fa94a347862f2a95d
https://doi.org/10.1109/icdmw.2019.00096
https://doi.org/10.1109/icdmw.2019.00096
Autor:
Donglin Wang, Sibo Gai
Publikováno v:
2019 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI).
Few-shot meta learning aims to obtain a prior from previous experiences, which is well used for new tasks during meta-test phase. The model-agnostic meta-learning (MAML) algorithm in [3] achieves this goal by finding a proper initial parameter at met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::465bd3e16f02d305d30293748dad1f8f
https://doi.org/10.1109/cchi.2019.8901909
https://doi.org/10.1109/cchi.2019.8901909
Publikováno v:
PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030298937
PRICAI (3)
PRICAI (3)
Collaborative filtering (CF) is among the most effective techniques for recommendations. However, it suffers from data sparsity and cold-start issue. One solution is to incorporate the side information and the other is to learn knowledge from relevan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a90397dc40c1e097898078a90c6fbfc
https://doi.org/10.1007/978-3-030-29894-4_42
https://doi.org/10.1007/978-3-030-29894-4_42
