Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization

In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a priori for each unseen instance. In this paper, this problem is addressed in the way that a neural network algorithm named BP-MLL, i.e., backprop...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on knowledge and data engineering Ročník 18; číslo 10; s. 1338 - 1351
Hlavní autoři:	ZHANG, Min-Ling, ZHOU, Zhi-Hua
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York, NY IEEE 01.10.2006 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Applied sciences Artificial intelligence Back propagation backpropagation Backpropagation algorithms Biochemistry Bioinformatics Computer science; control theory; systems Connectionism. Neural networks Data mining Error functions Exact sciences and technology functional genomics Genomics Government Information systems. Data bases Labels Layout Learning Learning systems Machine learning Memory organisation. Data processing multilabel learning Neural networks Software Tasks Text categorization Texts Genomics neural networks text categorization Information extraction functional genomics multilabel learning Neural network Data mining Backpropagation algorithm Machine learning backpropagation Linguistics Learning algorithm
ISSN:	1041-4347, 1558-2191
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In multilabel learning, each instance in the training set is associated with a set of labels and the task is to output a label set whose size is unknown a priori for each unseen instance. In this paper, this problem is addressed in the way that a neural network algorithm named BP-MLL, i.e., backpropagation for multilabel learning, is proposed. It is derived from the popular backpropagation algorithm through employing a novel error function capturing the characteristics of multilabel learning, i.e., the labels belonging to an instance should be ranked higher than those not belonging to that instance. Applications to two real-world multilabel learning problems, i.e., functional genomics and text categorization, show that the performance of BP-MLL is superior to that of some well-established multilabel learning algorithms
Bibliografie:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 content type line 23
ISSN:	1041-4347 1558-2191
DOI:	10.1109/TKDE.2006.162