Matches in SemOpenAlex for { <https://semopenalex.org/work/W1565765145> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W1565765145 abstract "In a great variety of neuron models, neural inputs are combined using the summing operation. We introduce the concept of multiplicative neural networks that contain units that multiply their inputs instead of summing them and thus allow inputs to interact nonlinearly. The class of multiplicative neural networks comprises such widely known and well-studied network types as higher-order networks and product unit networks.We investigate the complexity of computing and learning for multiplicative neural networks. In particular, we derive upper and lower bounds on the Vapnik-Chervonenkis (VC) dimension and the pseudodimension for various types of networks with multiplicative units. As the most general case, we consider feedforward networks consisting of product and sigmoidal units, showing that their pseudo-dimension is bounded from above by a polynomial with the same order of magnitude as the currently best-known bound for purely sigmoidal networks. Moreover, we show that this bound holds even when the unit type, product or sigmoidal, may be learned. Crucial for these results are calculations of solution set components bounds for new network classes. As to lower bounds, we construct product unit networks of fixed depth with superlinear VC dimension.For sigmoidal networks of higher order, we establish polynomial bounds that, in contrast to previous results, do not involve any restriction of the network order. We further consider various classes of higher-order units, also known as sigma-pi units, that are characterized by connectivity constraints. In terms of these, we derive some asymptotically tight bounds.Multiplication plays an important role in both neural modeling of biological behavior and computing and learning with artificial neural networks. We briefly survey research in biology and in applications where multiplication is considered an essential computational element. The results we present here provide new tools for assessing the impact of multiplication on the computational power and the learning capabilities of neural networks." @default.
- W1565765145 created "2016-06-24" @default.
- W1565765145 creator A5058601965 @default.
- W1565765145 date "2000-01-01" @default.
- W1565765145 modified "2023-09-24" @default.
- W1565765145 title "On the Complexity of Computing and Learning with Multiplicative Neural Networks" @default.
- W1565765145 hasPublicationYear "2000" @default.
- W1565765145 type Work @default.
- W1565765145 sameAs 1565765145 @default.
- W1565765145 citedByCount "0" @default.
- W1565765145 crossrefType "journal-article" @default.
- W1565765145 hasAuthorship W1565765145A5058601965 @default.
- W1565765145 hasConcept C10138342 @default.
- W1565765145 hasConcept C114614502 @default.
- W1565765145 hasConcept C118615104 @default.
- W1565765145 hasConcept C119322782 @default.
- W1565765145 hasConcept C134306372 @default.
- W1565765145 hasConcept C154945302 @default.
- W1565765145 hasConcept C162324750 @default.
- W1565765145 hasConcept C182306322 @default.
- W1565765145 hasConcept C2524010 @default.
- W1565765145 hasConcept C33676613 @default.
- W1565765145 hasConcept C33923547 @default.
- W1565765145 hasConcept C34388435 @default.
- W1565765145 hasConcept C41008148 @default.
- W1565765145 hasConcept C42747912 @default.
- W1565765145 hasConcept C47702885 @default.
- W1565765145 hasConcept C50644808 @default.
- W1565765145 hasConcept C77553402 @default.
- W1565765145 hasConcept C81388566 @default.
- W1565765145 hasConcept C90119067 @default.
- W1565765145 hasConcept C90673727 @default.
- W1565765145 hasConceptScore W1565765145C10138342 @default.
- W1565765145 hasConceptScore W1565765145C114614502 @default.
- W1565765145 hasConceptScore W1565765145C118615104 @default.
- W1565765145 hasConceptScore W1565765145C119322782 @default.
- W1565765145 hasConceptScore W1565765145C134306372 @default.
- W1565765145 hasConceptScore W1565765145C154945302 @default.
- W1565765145 hasConceptScore W1565765145C162324750 @default.
- W1565765145 hasConceptScore W1565765145C182306322 @default.
- W1565765145 hasConceptScore W1565765145C2524010 @default.
- W1565765145 hasConceptScore W1565765145C33676613 @default.
- W1565765145 hasConceptScore W1565765145C33923547 @default.
- W1565765145 hasConceptScore W1565765145C34388435 @default.
- W1565765145 hasConceptScore W1565765145C41008148 @default.
- W1565765145 hasConceptScore W1565765145C42747912 @default.
- W1565765145 hasConceptScore W1565765145C47702885 @default.
- W1565765145 hasConceptScore W1565765145C50644808 @default.
- W1565765145 hasConceptScore W1565765145C77553402 @default.
- W1565765145 hasConceptScore W1565765145C81388566 @default.
- W1565765145 hasConceptScore W1565765145C90119067 @default.
- W1565765145 hasConceptScore W1565765145C90673727 @default.
- W1565765145 hasLocation W15657651451 @default.
- W1565765145 hasOpenAccess W1565765145 @default.
- W1565765145 hasPrimaryLocation W15657651451 @default.
- W1565765145 hasRelatedWork W1489327613 @default.
- W1565765145 hasRelatedWork W1508957419 @default.
- W1565765145 hasRelatedWork W1970523910 @default.
- W1565765145 hasRelatedWork W1994888168 @default.
- W1565765145 hasRelatedWork W2034797247 @default.
- W1565765145 hasRelatedWork W2103702921 @default.
- W1565765145 hasRelatedWork W2109292177 @default.
- W1565765145 hasRelatedWork W2154402823 @default.
- W1565765145 hasRelatedWork W2158368251 @default.
- W1565765145 hasRelatedWork W2400263421 @default.
- W1565765145 hasRelatedWork W2739309726 @default.
- W1565765145 hasRelatedWork W2912753314 @default.
- W1565765145 hasRelatedWork W2951603627 @default.
- W1565765145 hasRelatedWork W2962715412 @default.
- W1565765145 hasRelatedWork W2963221924 @default.
- W1565765145 hasRelatedWork W2968808847 @default.
- W1565765145 hasRelatedWork W2982376398 @default.
- W1565765145 hasRelatedWork W3177032538 @default.
- W1565765145 hasRelatedWork W3187522787 @default.
- W1565765145 hasRelatedWork W3213639461 @default.
- W1565765145 hasVolume "7" @default.
- W1565765145 isParatext "false" @default.
- W1565765145 isRetracted "false" @default.
- W1565765145 magId "1565765145" @default.
- W1565765145 workType "article" @default.