Results 271 to 280 of about 168,521,757 (307)
Some of the next articles are maybe not open access.
Proceedings of the 20th ACM international conference on Information and knowledge management, 2011
Active learning traditionally assumes that labeled and unlabeled samples are subject to the same distributions and the goal of an active learner is to label the most informative unlabeled samples. In reality, situations may exist that we may not have unlabeled samples from the same domain as the labeled samples (i.e.
Zhenfeng Zhu +4 more
openaire +2 more sources
Active learning traditionally assumes that labeled and unlabeled samples are subject to the same distributions and the goal of an active learner is to label the most informative unlabeled samples. In reality, situations may exist that we may not have unlabeled samples from the same domain as the labeled samples (i.e.
Zhenfeng Zhu +4 more
openaire +2 more sources
Interhemispheric transfer of learning
Life Sciences, 1965Abstract Interhemispheric transfer of a simple discrimination was studied by means of spreading cortical depression. Following a single trial with both hemispheres functional transfer to the untrained hemisphere did not occur if SD was elicited in either hemisphere fifteen seconds after the transfer trial.
O S, RAY, G, EMLEY
openaire +2 more sources
Transfer Learning and Ensemble Learning
2020In this chapter, we start from transfer learning and introduce the relationship between different learners; we use ensemble learning to combine them together and hope to get a strong learner from a weak learner by changing the training dataset or adjusting parameters of networks. Our ultimate goal is to implement a robust and stable classifier.
openaire +1 more source
Boosting for transfer learning
Proceedings of the 24th international conference on Machine learning, 2007Traditional machine learning makes a basic assumption: the training and test data should be under the same distribution. However, in many cases, this identical-distribution assumption does not hold. The assumption might be violated when a task from one new domain comes, while there are only labeled data from a similar old domain.
Wenyuan Dai +3 more
openaire +1 more source
Transfer Learning by Kernel Meta-Learning.
, 2012 A crucial issue in machine learning is how to learn appropriate representations for data. Recently, much work has been devoted to kernel learning, that is, the problem of finding a good kernel matrix for a given task. This can be done in a semi-supervised learning setting by using a large set of unlabeled data and a (typically small) set of i.i.d ...
AIOLLI, FABIO
openaire +3 more sources
Neurocomputing
Transfer learning is aimed at supporting the design of machine learning models in the target domain Dt, given that the knowledge (model) has already been constructed in the source domain Ds. The domains Dtand Ds (as well as the corresponding tasks Ts and Tt) are similar, yet not identical.
Al-Hmouz, Rami +3 more
openaire +3 more sources
Transfer learning is aimed at supporting the design of machine learning models in the target domain Dt, given that the knowledge (model) has already been constructed in the source domain Ds. The domains Dtand Ds (as well as the corresponding tasks Ts and Tt) are similar, yet not identical.
Al-Hmouz, Rami +3 more
openaire +3 more sources
Learning Transfers via Transfer Learning
2021 IEEE Workshop on Innovating the Network for Data-Intensive Science (INDIS), 2021Md. Arifuzzaman, Engin Arslan
openaire +1 more source
Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015
Transfer learning, which leverages knowledge from source domains to enhance learning ability in a target domain, has been proven effective in various applications. One major limitation of transfer learning is that the source and target domains should be directly related.
Ben Tan +3 more
openaire +1 more source
Transfer learning, which leverages knowledge from source domains to enhance learning ability in a target domain, has been proven effective in various applications. One major limitation of transfer learning is that the source and target domains should be directly related.
Ben Tan +3 more
openaire +1 more source
An Introduction to Transfer Learning
2008Many existing data mining and machine learning techniques are based on the assumption that training and test data fit the same distribution. This assumption does not hold, however, as in many cases of Web mining and wireless computing when labeled data becomes outdated or test data are from a different domain with training data.
openaire +1 more source