Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002746> ?p ?o ?g. }
- W4386002746 endingPage "265" @default.
- W4386002746 startingPage "244" @default.
- W4386002746 abstract "A multilayered bidirectional associative memory neural network is proposed to account for learning nonlinear types of association. The model (denoted as the MF-BAM) is composed of two modules, the Multi-Feature extracting bidirectional associative memory (MF), which contains various unsupervised network layers, and a modified Bidirectional Associative Memory (BAM), which consists of a single supervised network layer. The MF generates successive feature patterns from the original inputs. These patterns change the relationship between the inputs and targets in a way that the BAM can learn. The model was tested on different nonlinear tasks, such as the N-bit, Double Moon and its variants, and the 3-class spiral task. Behaviors were reported through learning errors, decision zones, and recall performances. Results showed that it was possible to learn all tasks consistently. By manipulating the number of units per layer and the number of unsupervised network layers in the MF, it was possible to change the level of nonlinearity observed in the decision boundaries. Furthermore, results indicated that different behaviors were achieved from the same set of inputs by using the different generated patterns. These findings are significant as they showed how a BAM-inspired model could solve nonlinear tasks in a more cognitively plausible fashion." @default.
- W4386002746 created "2023-08-20" @default.
- W4386002746 creator A5015138506 @default.
- W4386002746 creator A5040824367 @default.
- W4386002746 creator A5073154994 @default.
- W4386002746 date "2023-10-01" @default.
- W4386002746 modified "2023-10-18" @default.
- W4386002746 title "A multilayered bidirectional associative memory model for learning nonlinear tasks" @default.
- W4386002746 cites W1498436455 @default.
- W4386002746 cites W1592398236 @default.
- W4386002746 cites W1854169473 @default.
- W4386002746 cites W188937245 @default.
- W4386002746 cites W1983731822 @default.
- W4386002746 cites W1985976674 @default.
- W4386002746 cites W1986868156 @default.
- W4386002746 cites W1989296422 @default.
- W4386002746 cites W1990150421 @default.
- W4386002746 cites W1995341919 @default.
- W4386002746 cites W2003952197 @default.
- W4386002746 cites W2011487458 @default.
- W4386002746 cites W2013768250 @default.
- W4386002746 cites W2014323024 @default.
- W4386002746 cites W2022616811 @default.
- W4386002746 cites W2026738815 @default.
- W4386002746 cites W2044925158 @default.
- W4386002746 cites W2051531749 @default.
- W4386002746 cites W2057227931 @default.
- W4386002746 cites W2057529293 @default.
- W4386002746 cites W2058960948 @default.
- W4386002746 cites W2063993331 @default.
- W4386002746 cites W2066524437 @default.
- W4386002746 cites W2082241885 @default.
- W4386002746 cites W2082622165 @default.
- W4386002746 cites W2083758028 @default.
- W4386002746 cites W2095425517 @default.
- W4386002746 cites W2100823705 @default.
- W4386002746 cites W2103252469 @default.
- W4386002746 cites W2106304233 @default.
- W4386002746 cites W2107786698 @default.
- W4386002746 cites W2110278466 @default.
- W4386002746 cites W2112314142 @default.
- W4386002746 cites W2113064032 @default.
- W4386002746 cites W2122988375 @default.
- W4386002746 cites W2128084896 @default.
- W4386002746 cites W2129217160 @default.
- W4386002746 cites W2135576811 @default.
- W4386002746 cites W2138727659 @default.
- W4386002746 cites W2145643383 @default.
- W4386002746 cites W2145700613 @default.
- W4386002746 cites W2152220402 @default.
- W4386002746 cites W2152742558 @default.
- W4386002746 cites W2153342234 @default.
- W4386002746 cites W2171278097 @default.
- W4386002746 cites W2257979135 @default.
- W4386002746 cites W2484002554 @default.
- W4386002746 cites W2557728737 @default.
- W4386002746 cites W2615393670 @default.
- W4386002746 cites W2725150524 @default.
- W4386002746 cites W2743151379 @default.
- W4386002746 cites W2750419148 @default.
- W4386002746 cites W2783380896 @default.
- W4386002746 cites W2785211320 @default.
- W4386002746 cites W2800355443 @default.
- W4386002746 cites W2904474124 @default.
- W4386002746 cites W2914602189 @default.
- W4386002746 cites W2921495890 @default.
- W4386002746 cites W2969588018 @default.
- W4386002746 cites W2971683016 @default.
- W4386002746 cites W2982316857 @default.
- W4386002746 cites W2995012499 @default.
- W4386002746 cites W3023596111 @default.
- W4386002746 cites W3029588370 @default.
- W4386002746 cites W3111093125 @default.
- W4386002746 cites W3118643537 @default.
- W4386002746 cites W3193182698 @default.
- W4386002746 cites W4240778903 @default.
- W4386002746 doi "https://doi.org/10.1016/j.neunet.2023.08.018" @default.
- W4386002746 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37660673" @default.
- W4386002746 hasPublicationYear "2023" @default.
- W4386002746 type Work @default.
- W4386002746 citedByCount "0" @default.
- W4386002746 crossrefType "journal-article" @default.
- W4386002746 hasAuthorship W4386002746A5015138506 @default.
- W4386002746 hasAuthorship W4386002746A5040824367 @default.
- W4386002746 hasAuthorship W4386002746A5073154994 @default.
- W4386002746 hasBestOaLocation W43860027461 @default.
- W4386002746 hasConcept C120620853 @default.
- W4386002746 hasConcept C121332964 @default.
- W4386002746 hasConcept C138885662 @default.
- W4386002746 hasConcept C153180895 @default.
- W4386002746 hasConcept C154945302 @default.
- W4386002746 hasConcept C158622935 @default.
- W4386002746 hasConcept C159423971 @default.
- W4386002746 hasConcept C162324750 @default.
- W4386002746 hasConcept C177264268 @default.
- W4386002746 hasConcept C178790620 @default.
- W4386002746 hasConcept C185592680 @default.
- W4386002746 hasConcept C187736073 @default.