Deep Learning - CISMeF

Preferred Label : Deep Learning;

MeSH definition : Supervised or unsupervised machine learning methods that use multiple layers of data representations generated by nonlinear transformations, instead of individual task-specific ALGORITHMS, to build and train neural network models.;

Définition CISMeF : A specialized branch of ML that involves training neural networks with multiple intermediary (hidden) layers that operate between an input layer that receives data and an output layer that presents the final network output. Each layer learns to transform its input data into a slightly more abstract and composite representation and produces an output that serves as an input for the next layer. As data propagates through successive layers, these models are able to learn hierarchical feature representations from the input data. For example, in healthcare, deep learning models can be used to identify tumors or suspicious lesions in medical images to support physicians and radiologists in the evaluation of disease.; Source: Adapted from: Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-zExternal Link Disclaimer International Organization for Standardization. (2020). Software and systems engineering — Software testing — Part 11: Guidelines on the testing of AI-based systems (ISO/IEC TR 29119-11:2020). https://www.iso.org/standard/79016.html;

MeSH synonym : Learning, Deep; Hierarchical Learning; Learning, Hierarchical;

CISMeF synonym : deep structured learning; hierarchical learning;

Origin ID

D000077321;

UMLS CUI

C4704761;

Allowable qualifiers
- classification [MeSH Qualifier]
- economics [MeSH Qualifier]
- ethics [MeSH Qualifier]
- history [MeSH Qualifier]
- legislation and jurisprudence [MeSH Qualifier]
- standards [MeSH Qualifier]
- statistics and numerical data [MeSH Qualifier]
- supply and distribution [MeSH Qualifier]
- trends [MeSH Qualifier]
CISMeF manual mappings
- Deep Learning [EFMI term]
Record concept(s)
- Deep Learning [MeSH concept]
Semantic type(s)
- Machine Activity [UMLS semantic type]
UMLS correspondences (same concept)
- Deep Learning [EFMI term]
- Deep Learning [NCIt concept]

Keyword's position in hierarchy(ies) :

Details

Main resources

You can consult :