FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2395092015> ?p ?o ?g. }

• W2395092015 abstract "We consider deep neural networks, in which the output of each node is a quadratic function of its inputs. Similar to other deep architectures, these networks can compactly represent any function on a finite training set. The main goal of this paper is the derivation of an efficient layer-by-layer algorithm for training such networks, which we denote as the emph{Basis Learner}. The algorithm is a universal learner in the sense that the training error is guaranteed to decrease at every iteration, and can eventually reach zero under mild conditions. We present practical implementations of this algorithm, as well as preliminary experimental results. We also compare our deep architecture to other shallow architectures for learning polynomials, in particular kernel learning." @default.
• W2395092015 created "2016-06-24" @default.
• W2395092015 creator A5017753135 @default.
• W2395092015 creator A5078263052 @default.
• W2395092015 creator A5089862531 @default.
• W2395092015 date "2013-04-26" @default.
• W2395092015 modified "2023-09-26" @default.
• W2395092015 title "A Provably Efficient Algorithm for Training Deep Networks" @default.
• W2395092015 cites W108223363 @default.
• W2395092015 cites W1498436455 @default.
• W2395092015 cites W1538131130 @default.
• W2395092015 cites W1542886316 @default.
• W2395092015 cites W1544148964 @default.
• W2395092015 cites W1560724230 @default.
• W2395092015 cites W1982662469 @default.
• W2395092015 cites W1994197834 @default.
• W2395092015 cites W2072128103 @default.
• W2395092015 cites W2079751279 @default.
• W2395092015 cites W2102380305 @default.
• W2395092015 cites W2117130368 @default.
• W2395092015 cites W2117756735 @default.
• W2395092015 cites W2120480077 @default.
• W2395092015 cites W2130325614 @default.
• W2395092015 cites W2136922672 @default.
• W2395092015 cites W2139427956 @default.
• W2395092015 cites W2141473882 @default.
• W2395092015 cites W2167608136 @default.
• W2395092015 cites W2253807446 @default.
• W2395092015 cites W2264065105 @default.
• W2395092015 cites W2399803916 @default.
• W2395092015 cites W2613634265 @default.
• W2395092015 hasPublicationYear "2013" @default.
• W2395092015 type Work @default.
• W2395092015 sameAs 2395092015 @default.
• W2395092015 citedByCount "14" @default.
• W2395092015 countsByYear W23950920152013 @default.
• W2395092015 countsByYear W23950920152014 @default.
• W2395092015 countsByYear W23950920152015 @default.
• W2395092015 countsByYear W23950920152016 @default.
• W2395092015 countsByYear W23950920152017 @default.
• W2395092015 countsByYear W23950920152018 @default.
• W2395092015 countsByYear W23950920152020 @default.
• W2395092015 crossrefType "posted-content" @default.
• W2395092015 hasAuthorship W2395092015A5017753135 @default.
• W2395092015 hasAuthorship W2395092015A5078263052 @default.
• W2395092015 hasAuthorship W2395092015A5089862531 @default.
• W2395092015 hasConcept C108583219 @default.
• W2395092015 hasConcept C11413529 @default.
• W2395092015 hasConcept C118615104 @default.
• W2395092015 hasConcept C121332964 @default.
• W2395092015 hasConcept C127413603 @default.
• W2395092015 hasConcept C129844170 @default.
• W2395092015 hasConcept C14036430 @default.
• W2395092015 hasConcept C153294291 @default.
• W2395092015 hasConcept C154945302 @default.
• W2395092015 hasConcept C177264268 @default.
• W2395092015 hasConcept C178790620 @default.
• W2395092015 hasConcept C185592680 @default.
• W2395092015 hasConcept C199360897 @default.
• W2395092015 hasConcept C2524010 @default.
• W2395092015 hasConcept C26713055 @default.
• W2395092015 hasConcept C2777211547 @default.
• W2395092015 hasConcept C2779227376 @default.
• W2395092015 hasConcept C33923547 @default.
• W2395092015 hasConcept C41008148 @default.
• W2395092015 hasConcept C50644808 @default.
• W2395092015 hasConcept C62611344 @default.
• W2395092015 hasConcept C66938386 @default.
• W2395092015 hasConcept C74193536 @default.
• W2395092015 hasConcept C78458016 @default.
• W2395092015 hasConcept C86803240 @default.
• W2395092015 hasConceptScore W2395092015C108583219 @default.
• W2395092015 hasConceptScore W2395092015C11413529 @default.
• W2395092015 hasConceptScore W2395092015C118615104 @default.
• W2395092015 hasConceptScore W2395092015C121332964 @default.
• W2395092015 hasConceptScore W2395092015C127413603 @default.
• W2395092015 hasConceptScore W2395092015C129844170 @default.
• W2395092015 hasConceptScore W2395092015C14036430 @default.
• W2395092015 hasConceptScore W2395092015C153294291 @default.
• W2395092015 hasConceptScore W2395092015C154945302 @default.
• W2395092015 hasConceptScore W2395092015C177264268 @default.
• W2395092015 hasConceptScore W2395092015C178790620 @default.
• W2395092015 hasConceptScore W2395092015C185592680 @default.
• W2395092015 hasConceptScore W2395092015C199360897 @default.
• W2395092015 hasConceptScore W2395092015C2524010 @default.
• W2395092015 hasConceptScore W2395092015C26713055 @default.
• W2395092015 hasConceptScore W2395092015C2777211547 @default.
• W2395092015 hasConceptScore W2395092015C2779227376 @default.
• W2395092015 hasConceptScore W2395092015C33923547 @default.
• W2395092015 hasConceptScore W2395092015C41008148 @default.
• W2395092015 hasConceptScore W2395092015C50644808 @default.
• W2395092015 hasConceptScore W2395092015C62611344 @default.
• W2395092015 hasConceptScore W2395092015C66938386 @default.
• W2395092015 hasConceptScore W2395092015C74193536 @default.
• W2395092015 hasConceptScore W2395092015C78458016 @default.
• W2395092015 hasConceptScore W2395092015C86803240 @default.
• W2395092015 hasLocation W23950920151 @default.
• W2395092015 hasOpenAccess W2395092015 @default.
• W2395092015 hasPrimaryLocation W23950920151 @default.
• W2395092015 hasRelatedWork W1542886316 @default.

• next