Representation learning: a review and new perspectives - PubMed (original) (raw)
Review
. 2013 Aug;35(8):1798-828.
doi: 10.1109/TPAMI.2013.50.
Affiliations
- PMID: 23787338
- DOI: 10.1109/TPAMI.2013.50
Review
Representation learning: a review and new perspectives
Yoshua Bengio et al. IEEE Trans Pattern Anal Mach Intell. 2013 Aug.
Abstract
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks. This motivates longer term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation, and manifold learning.
Similar articles
- Data Integration Using Advances in Machine Learning in Drug Discovery and Molecular Biology.
Hudson IL. Hudson IL. Methods Mol Biol. 2021;2190:167-184. doi: 10.1007/978-1-0716-0826-5_7. Methods Mol Biol. 2021. PMID: 32804365 Review. - Towards spike-based machine intelligence with neuromorphic computing.
Roy K, Jaiswal A, Panda P. Roy K, et al. Nature. 2019 Nov;575(7784):607-617. doi: 10.1038/s41586-019-1677-2. Epub 2019 Nov 27. Nature. 2019. PMID: 31776490 Review. - Deep neural networks in psychiatry.
Durstewitz D, Koppe G, Meyer-Lindenberg A. Durstewitz D, et al. Mol Psychiatry. 2019 Nov;24(11):1583-1598. doi: 10.1038/s41380-019-0365-9. Epub 2019 Feb 15. Mol Psychiatry. 2019. PMID: 30770893 Review. - Could advances in representation learning in Artificial Intelligence provide the new paradigm for data integration in drug discovery?
Vijayan V, Rouillard AD, Rajpal DK, Agarwal P. Vijayan V, et al. Expert Opin Drug Discov. 2019 Mar;14(3):191-194. doi: 10.1080/17460441.2019.1573811. Epub 2019 Jan 30. Expert Opin Drug Discov. 2019. PMID: 30696299 No abstract available. - Engineering a Less Artificial Intelligence.
Sinz FH, Pitkow X, Reimer J, Bethge M, Tolias AS. Sinz FH, et al. Neuron. 2019 Sep 25;103(6):967-979. doi: 10.1016/j.neuron.2019.08.034. Neuron. 2019. PMID: 31557461 Review.
Cited by
- PATTERN: Pain Assessment for paTients who can't TEll using Restricted Boltzmann machiNe.
Yang L, Wang S, Jiang X, Cheng S, Kim HE. Yang L, et al. BMC Med Inform Decis Mak. 2016 Jul 25;16 Suppl 3(Suppl 3):73. doi: 10.1186/s12911-016-0317-0. BMC Med Inform Decis Mak. 2016. PMID: 27454233 Free PMC article. - A Robust Deep Model for Improved Classification of AD/MCI Patients.
Li F, Tran L, Thung KH, Ji S, Shen D, Li J. Li F, et al. IEEE J Biomed Health Inform. 2015 Sep;19(5):1610-6. doi: 10.1109/JBHI.2015.2429556. Epub 2015 May 4. IEEE J Biomed Health Inform. 2015. PMID: 25955998 Free PMC article. - scSemiProfiler: Advancing large-scale single-cell studies through semi-profiling with deep generative models and active learning.
Wang J, Fonseca GJ, Ding J. Wang J, et al. Nat Commun. 2024 Jul 16;15(1):5989. doi: 10.1038/s41467-024-50150-1. Nat Commun. 2024. PMID: 39013867 Free PMC article. - Learning adaptive representations for entity recognition in the biomedical domain.
Lauriola I, Aiolli F, Lavelli A, Rinaldi F. Lauriola I, et al. J Biomed Semantics. 2021 May 17;12(1):10. doi: 10.1186/s13326-021-00238-0. J Biomed Semantics. 2021. PMID: 34001263 Free PMC article. - Improving Diagnosis of Depression With XGBOOST Machine Learning Model and a Large Biomarkers Dutch Dataset (n = 11,081).
Sharma A, Verbeke WJMI. Sharma A, et al. Front Big Data. 2020 Apr 30;3:15. doi: 10.3389/fdata.2020.00015. eCollection 2020. Front Big Data. 2020. PMID: 33693389 Free PMC article.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources