FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2031878488> ?p ?o ?g. }

• W2031878488 endingPage "29" @default.
• W2031878488 startingPage "18" @default.
• W2031878488 abstract "Extreme learning machine (ELM), which was originally proposed for generalized single-hidden layer feedforward neural networks (SLFNs), provides efficient unified learning solutions for the applications of feature learning, clustering, regression and classification. Different from the common understanding and tenet that hidden neurons of neural networks need to be iteratively adjusted during training stage, ELM theories show that hidden neurons are important but need not be iteratively tuned. In fact, all the parameters of hidden nodes can be independent of training samples and randomly generated according to any continuous probability distribution. And the obtained ELM networks satisfy universal approximation and classification capability. The fully connected ELM architecture has been extensively studied. However, ELM with local connections has not attracted much research attention yet. This paper studies the general architecture of locally connected ELM, showing that: 1) ELM theories are naturally valid for local connections, thus introducing local receptive fields to the input layer; 2) each hidden node in ELM can be a combination of several hidden nodes (a subnetwork), which is also consistent with ELM theories. ELM theories may shed a light on the research of different local receptive fields including true biological receptive fields of which the exact shapes and formula may be unknown to human beings. As a specific example of such general architectures, random convolutional nodes and a pooling structure are implemented in this paper. Experimental results on the NORB dataset, a benchmark for object recognition, show that compared with conventional deep learning solutions, the proposed local receptive fields based ELM (ELM-LRF) reduces the error rate from 6.5% to 2.7% and increases the learning speed up to 200 times." @default.
• W2031878488 created "2016-06-24" @default.
• W2031878488 creator A5008300079 @default.
• W2031878488 creator A5049390322 @default.
• W2031878488 creator A5061746912 @default.
• W2031878488 creator A5076922237 @default.
• W2031878488 date "2015-05-01" @default.
• W2031878488 modified "2023-10-09" @default.
• W2031878488 title "Local Receptive Fields Based Extreme Learning Machine" @default.
• W2031878488 cites W1498436455 @default.
• W2031878488 cites W1970699372 @default.
• W2031878488 cites W1973433968 @default.
• W2031878488 cites W1978581090 @default.
• W2031878488 cites W1980713635 @default.
• W2031878488 cites W1983946671 @default.
• W2031878488 cites W1986278072 @default.
• W2031878488 cites W1990938413 @default.
• W2031878488 cites W1996640396 @default.
• W2031878488 cites W2010353187 @default.
• W2031878488 cites W2017212187 @default.
• W2031878488 cites W2026131661 @default.
• W2031878488 cites W2026466111 @default.
• W2031878488 cites W2039333275 @default.
• W2031878488 cites W2042184006 @default.
• W2031878488 cites W2046322491 @default.
• W2031878488 cites W2052164429 @default.
• W2031878488 cites W2072536676 @default.
• W2031878488 cites W2083357246 @default.
• W2031878488 cites W2084642506 @default.
• W2031878488 cites W2085932691 @default.
• W2031878488 cites W2093356195 @default.
• W2031878488 cites W2099579348 @default.
• W2031878488 cites W2101674911 @default.
• W2031878488 cites W2104242071 @default.
• W2031878488 cites W2109574129 @default.
• W2031878488 cites W2111072639 @default.
• W2031878488 cites W2117731089 @default.
• W2031878488 cites W2121971770 @default.
• W2031878488 cites W2122040390 @default.
• W2031878488 cites W2123223828 @default.
• W2031878488 cites W2130325614 @default.
• W2031878488 cites W2134557905 @default.
• W2031878488 cites W2141695047 @default.
• W2031878488 cites W2142947774 @default.
• W2031878488 cites W2144354855 @default.
• W2031878488 cites W2146904825 @default.
• W2031878488 cites W2153232138 @default.
• W2031878488 cites W2155910151 @default.
• W2031878488 cites W2157595416 @default.
• W2031878488 cites W2161055889 @default.
• W2031878488 cites W2162112159 @default.
• W2031878488 cites W2162392441 @default.
• W2031878488 cites W2163153337 @default.
• W2031878488 cites W2169181840 @default.
• W2031878488 cites W2532798880 @default.
• W2031878488 cites W2546302380 @default.
• W2031878488 cites W4231109964 @default.
• W2031878488 cites W4239510810 @default.
• W2031878488 cites W4244894666 @default.
• W2031878488 doi "https://doi.org/10.1109/mci.2015.2405316" @default.
• W2031878488 hasPublicationYear "2015" @default.
• W2031878488 type Work @default.
• W2031878488 sameAs 2031878488 @default.
• W2031878488 citedByCount "293" @default.
• W2031878488 countsByYear W20318784882015 @default.
• W2031878488 countsByYear W20318784882016 @default.
• W2031878488 countsByYear W20318784882017 @default.
• W2031878488 countsByYear W20318784882018 @default.
• W2031878488 countsByYear W20318784882019 @default.
• W2031878488 countsByYear W20318784882020 @default.
• W2031878488 countsByYear W20318784882021 @default.
• W2031878488 countsByYear W20318784882022 @default.
• W2031878488 countsByYear W20318784882023 @default.
• W2031878488 crossrefType "journal-article" @default.
• W2031878488 hasAuthorship W2031878488A5008300079 @default.
• W2031878488 hasAuthorship W2031878488A5049390322 @default.
• W2031878488 hasAuthorship W2031878488A5061746912 @default.
• W2031878488 hasAuthorship W2031878488A5076922237 @default.
• W2031878488 hasConcept C104317684 @default.
• W2031878488 hasConcept C108037233 @default.
• W2031878488 hasConcept C112313634 @default.
• W2031878488 hasConcept C119857082 @default.
• W2031878488 hasConcept C127413603 @default.
• W2031878488 hasConcept C127716648 @default.
• W2031878488 hasConcept C13280743 @default.
• W2031878488 hasConcept C133731056 @default.
• W2031878488 hasConcept C152153834 @default.
• W2031878488 hasConcept C153180895 @default.
• W2031878488 hasConcept C154945302 @default.
• W2031878488 hasConcept C156738730 @default.
• W2031878488 hasConcept C185592680 @default.
• W2031878488 hasConcept C185798385 @default.
• W2031878488 hasConcept C188082640 @default.
• W2031878488 hasConcept C19071747 @default.
• W2031878488 hasConcept C205649164 @default.
• W2031878488 hasConcept C2780150128 @default.
• W2031878488 hasConcept C2780186347 @default.
• W2031878488 hasConcept C38652104 @default.

• next