FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951470200> ?p ?o ?g. }

• W2951470200 abstract "In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks. The proposed $L_p$ unit receives signals from several projections of a subset of units in the layer below and computes a normalized $L_p$ norm. We notice two interesting interpretations of the $L_p$ unit. First, the proposed unit can be understood as a generalization of a number of conventional pooling operators such as average, root-mean-square and max pooling widely used in, for instance, convolutional neural networks (CNN), HMAX models and neocognitrons. Furthermore, the $L_p$ unit is, to a certain degree, similar to the recently proposed maxout unit (Goodfellow et al., 2013) which achieved the state-of-the-art object recognition results on a number of benchmark datasets. Secondly, we provide a geometrical interpretation of the activation function based on which we argue that the $L_p$ unit is more efficient at representing complex, nonlinear separating boundaries. Each $L_p$ unit defines a superelliptic boundary, with its exact shape defined by the order $p$. We claim that this makes it possible to model arbitrarily shaped, curved boundaries more efficiently by combining a few $L_p$ units of different orders. This insight justifies the need for learning different orders for each unit in the model. We empirically evaluate the proposed $L_p$ units on a number of datasets and show that multilayer perceptrons (MLP) consisting of the $L_p$ units achieve the state-of-the-art results on a number of benchmark datasets. Furthermore, we evaluate the proposed $L_p$ unit on the recently proposed deep recurrent neural networks (RNN)." @default.
• W2951470200 created "2019-06-27" @default.
• W2951470200 creator A5041145688 @default.
• W2951470200 creator A5043910056 @default.
• W2951470200 creator A5086198262 @default.
• W2951470200 creator A5091175785 @default.
• W2951470200 date "2013-11-07" @default.
• W2951470200 modified "2023-10-18" @default.
• W2951470200 title "Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks" @default.
• W2951470200 cites W1498436455 @default.
• W2951470200 cites W1569512666 @default.
• W2951470200 cites W1606347560 @default.
• W2951470200 cites W1665214252 @default.
• W2951470200 cites W171902450 @default.
• W2951470200 cites W1814328102 @default.
• W2951470200 cites W1815076433 @default.
• W2951470200 cites W1819710477 @default.
• W2951470200 cites W1844261860 @default.
• W2951470200 cites W1864026867 @default.
• W2951470200 cites W1872489089 @default.
• W2951470200 cites W1889624880 @default.
• W2951470200 cites W1904365287 @default.
• W2951470200 cites W2008353316 @default.
• W2951470200 cites W2065436347 @default.
• W2951470200 cites W2074551195 @default.
• W2951470200 cites W2097018403 @default.
• W2951470200 cites W2097998348 @default.
• W2951470200 cites W2101926813 @default.
• W2951470200 cites W2108069432 @default.
• W2951470200 cites W2111244981 @default.
• W2951470200 cites W2112796928 @default.
• W2951470200 cites W2115701093 @default.
• W2951470200 cites W2117731089 @default.
• W2951470200 cites W2139427956 @default.
• W2951470200 cites W2149194912 @default.
• W2951470200 cites W2166093887 @default.
• W2951470200 cites W2184045248 @default.
• W2951470200 cites W2546302380 @default.
• W2951470200 cites W2618530766 @default.
• W2951470200 cites W3037950864 @default.
• W2951470200 cites W3146803896 @default.
• W2951470200 cites W6908809 @default.
• W2951470200 hasPublicationYear "2013" @default.
• W2951470200 type Work @default.
• W2951470200 sameAs 2951470200 @default.
• W2951470200 citedByCount "3" @default.
• W2951470200 countsByYear W29514702002013 @default.
• W2951470200 countsByYear W29514702002014 @default.
• W2951470200 countsByYear W29514702002017 @default.
• W2951470200 crossrefType "posted-content" @default.
• W2951470200 hasAuthorship W2951470200A5041145688 @default.
• W2951470200 hasAuthorship W2951470200A5043910056 @default.
• W2951470200 hasAuthorship W2951470200A5086198262 @default.
• W2951470200 hasAuthorship W2951470200A5091175785 @default.
• W2951470200 hasConcept C108583219 @default.
• W2951470200 hasConcept C11413529 @default.
• W2951470200 hasConcept C114614502 @default.
• W2951470200 hasConcept C122637931 @default.
• W2951470200 hasConcept C13280743 @default.
• W2951470200 hasConcept C145420912 @default.
• W2951470200 hasConcept C153180895 @default.
• W2951470200 hasConcept C154945302 @default.
• W2951470200 hasConcept C17744445 @default.
• W2951470200 hasConcept C185798385 @default.
• W2951470200 hasConcept C191795146 @default.
• W2951470200 hasConcept C191948623 @default.
• W2951470200 hasConcept C199539241 @default.
• W2951470200 hasConcept C205649164 @default.
• W2951470200 hasConcept C33923547 @default.
• W2951470200 hasConcept C38365724 @default.
• W2951470200 hasConcept C41008148 @default.
• W2951470200 hasConcept C50644808 @default.
• W2951470200 hasConcept C60908668 @default.
• W2951470200 hasConcept C70437156 @default.
• W2951470200 hasConcept C81363708 @default.
• W2951470200 hasConceptScore W2951470200C108583219 @default.
• W2951470200 hasConceptScore W2951470200C11413529 @default.
• W2951470200 hasConceptScore W2951470200C114614502 @default.
• W2951470200 hasConceptScore W2951470200C122637931 @default.
• W2951470200 hasConceptScore W2951470200C13280743 @default.
• W2951470200 hasConceptScore W2951470200C145420912 @default.
• W2951470200 hasConceptScore W2951470200C153180895 @default.
• W2951470200 hasConceptScore W2951470200C154945302 @default.
• W2951470200 hasConceptScore W2951470200C17744445 @default.
• W2951470200 hasConceptScore W2951470200C185798385 @default.
• W2951470200 hasConceptScore W2951470200C191795146 @default.
• W2951470200 hasConceptScore W2951470200C191948623 @default.
• W2951470200 hasConceptScore W2951470200C199539241 @default.
• W2951470200 hasConceptScore W2951470200C205649164 @default.
• W2951470200 hasConceptScore W2951470200C33923547 @default.
• W2951470200 hasConceptScore W2951470200C38365724 @default.
• W2951470200 hasConceptScore W2951470200C41008148 @default.
• W2951470200 hasConceptScore W2951470200C50644808 @default.
• W2951470200 hasConceptScore W2951470200C60908668 @default.
• W2951470200 hasConceptScore W2951470200C70437156 @default.
• W2951470200 hasConceptScore W2951470200C81363708 @default.
• W2951470200 hasOpenAccess W2951470200 @default.
• W2951470200 hasRelatedWork W1523447316 @default.
• W2951470200 hasRelatedWork W1549825062 @default.
• W2951470200 hasRelatedWork W1985024762 @default.

• next