Matches in SemOpenAlex for { <https://semopenalex.org/work/W99004795> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W99004795 endingPage "71" @default.
- W99004795 startingPage "63" @default.
- W99004795 abstract "Neural networks have been a fruitful area of research. Classification is a prime field of application. A~network of a single artificial neuron—a perceptron—is an example. More complex recurrent topologies—Hopfield networks—act as associative memories. Feedforward networks also have many nodes, but they usually work as classifiers, where the training procedure resembles that of the perceptron. These networks have several layers, including an input layer, at least one hidden layer, and an output layer, representing the target classes. Increasing the number of neurons and hidden layers leads to computationally expensive, but extremely efficient learning machines, known as deep learning architectures. While the computational complexity of all neural networks is high, the actual training time is often reduced by using parallel computing resources." @default.
- W99004795 created "2016-06-24" @default.
- W99004795 creator A5056277018 @default.
- W99004795 date "2014-01-01" @default.
- W99004795 modified "2023-09-25" @default.
- W99004795 title "Pattern Recognition and Neural Networks" @default.
- W99004795 cites W2005374071 @default.
- W99004795 cites W2040870580 @default.
- W99004795 cites W2059146732 @default.
- W99004795 cites W2075357005 @default.
- W99004795 cites W2111072639 @default.
- W99004795 cites W2128084896 @default.
- W99004795 cites W2137983211 @default.
- W99004795 cites W2160815625 @default.
- W99004795 cites W2167982865 @default.
- W99004795 cites W2169976759 @default.
- W99004795 doi "https://doi.org/10.1016/b978-0-12-800953-6.00006-2" @default.
- W99004795 hasPublicationYear "2014" @default.
- W99004795 type Work @default.
- W99004795 sameAs 99004795 @default.
- W99004795 citedByCount "1" @default.
- W99004795 countsByYear W990047952021 @default.
- W99004795 crossrefType "book-chapter" @default.
- W99004795 hasAuthorship W99004795A5056277018 @default.
- W99004795 hasConcept C153180895 @default.
- W99004795 hasConcept C154945302 @default.
- W99004795 hasConcept C41008148 @default.
- W99004795 hasConcept C50644808 @default.
- W99004795 hasConceptScore W99004795C153180895 @default.
- W99004795 hasConceptScore W99004795C154945302 @default.
- W99004795 hasConceptScore W99004795C41008148 @default.
- W99004795 hasConceptScore W99004795C50644808 @default.
- W99004795 hasLocation W990047951 @default.
- W99004795 hasOpenAccess W99004795 @default.
- W99004795 hasPrimaryLocation W990047951 @default.
- W99004795 hasRelatedWork W1978450727 @default.
- W99004795 hasRelatedWork W2033914206 @default.
- W99004795 hasRelatedWork W2046077695 @default.
- W99004795 hasRelatedWork W2146076056 @default.
- W99004795 hasRelatedWork W2163371487 @default.
- W99004795 hasRelatedWork W2163831990 @default.
- W99004795 hasRelatedWork W2378160586 @default.
- W99004795 hasRelatedWork W2386387936 @default.
- W99004795 hasRelatedWork W3003836766 @default.
- W99004795 hasRelatedWork W4244943737 @default.
- W99004795 isParatext "false" @default.
- W99004795 isRetracted "false" @default.
- W99004795 magId "99004795" @default.
- W99004795 workType "book-chapter" @default.