Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904752712> ?p ?o ?g. }
- W2904752712 abstract "Supervised learning has long been attributed to several feed-forward neural circuits within the brain, with attention being paid to the cerebellar granular layer. The focus of this study is to evaluate the input activity representation of these feed-forward neural networks. The activity of cerebellar granule cells is conveyed by parallel fibers and translated into Purkinje cell activity; the sole output of the cerebellar cortex. The learning process at this parallel-fiber-to-Purkinje-cell connection makes each Purkinje cell sensitive to a set of specific cerebellar states, determined by the granule-cell activity during a certain time window. A Purkinje cell becomes sensitive to each neural input state and, consequently, the network operates as a function able to generate a desired output for each provided input by means of supervised learning. However, not all sets of Purkinje cell responses can be assigned to any set of input states due to the network's own limitations (inherent to the network neurobiological substrate), that is, not all input-output mapping can be learned. A limiting factor is the representation of the input states through granule-cell activity. The quality of this representation will determine the capacity of the network to learn a varied set of outputs. In this study we present an algorithm for evaluating quantitatively the level of compatibility/interference amongst a set of given cerebellar states according to their representation (granule-cell activation patterns) without the need for actually conducting simulations and network training. The algorithm input consists of a real-number matrix that codifies the activity level of every considered granule-cell in each state. The capability of this representation to generate a varied set of outputs is evaluated geometrically, thus resulting in a real number that assesses the goodness of the representation" @default.
- W2904752712 created "2018-12-22" @default.
- W2904752712 creator A5010055841 @default.
- W2904752712 creator A5023617574 @default.
- W2904752712 creator A5038861361 @default.
- W2904752712 creator A5042414439 @default.
- W2904752712 date "2018-12-14" @default.
- W2904752712 modified "2023-10-18" @default.
- W2904752712 title "A Metric for Evaluating Neural Input Representation in Supervised Learning Networks" @default.
- W2904752712 cites W138221695 @default.
- W2904752712 cites W1486852018 @default.
- W2904752712 cites W1516529420 @default.
- W2904752712 cites W1968010465 @default.
- W2904752712 cites W1978592900 @default.
- W2904752712 cites W1979096535 @default.
- W2904752712 cites W1989790828 @default.
- W2904752712 cites W1993740947 @default.
- W2904752712 cites W2002679708 @default.
- W2904752712 cites W2009980685 @default.
- W2904752712 cites W2011569542 @default.
- W2904752712 cites W2012592267 @default.
- W2904752712 cites W2014894062 @default.
- W2904752712 cites W2021789384 @default.
- W2904752712 cites W2042238916 @default.
- W2904752712 cites W2043325561 @default.
- W2904752712 cites W2046445123 @default.
- W2904752712 cites W2054302388 @default.
- W2904752712 cites W2054768162 @default.
- W2904752712 cites W2058499433 @default.
- W2904752712 cites W2060052647 @default.
- W2904752712 cites W2060054159 @default.
- W2904752712 cites W2064573518 @default.
- W2904752712 cites W2072365940 @default.
- W2904752712 cites W2076845962 @default.
- W2904752712 cites W2079967417 @default.
- W2904752712 cites W2086049536 @default.
- W2904752712 cites W2093356195 @default.
- W2904752712 cites W2103019454 @default.
- W2904752712 cites W2103870410 @default.
- W2904752712 cites W2110059807 @default.
- W2904752712 cites W2112465764 @default.
- W2904752712 cites W2123612003 @default.
- W2904752712 cites W2123742740 @default.
- W2904752712 cites W2123820663 @default.
- W2904752712 cites W2126227320 @default.
- W2904752712 cites W2128862553 @default.
- W2904752712 cites W2134927362 @default.
- W2904752712 cites W2138603786 @default.
- W2904752712 cites W2141364242 @default.
- W2904752712 cites W2144676589 @default.
- W2904752712 cites W2145781990 @default.
- W2904752712 cites W2153504150 @default.
- W2904752712 cites W2155051950 @default.
- W2904752712 cites W2161299805 @default.
- W2904752712 cites W2165095254 @default.
- W2904752712 cites W2168558032 @default.
- W2904752712 cites W2168851497 @default.
- W2904752712 cites W2186699875 @default.
- W2904752712 cites W2304447290 @default.
- W2904752712 cites W2315788237 @default.
- W2904752712 cites W2341128634 @default.
- W2904752712 cites W2497264409 @default.
- W2904752712 cites W2520514017 @default.
- W2904752712 cites W2599737116 @default.
- W2904752712 cites W2951200949 @default.
- W2904752712 cites W3099967679 @default.
- W2904752712 cites W4238614602 @default.
- W2904752712 cites W4247763225 @default.
- W2904752712 cites W4253214256 @default.
- W2904752712 cites W4295151229 @default.
- W2904752712 cites W2048785661 @default.
- W2904752712 cites W2185212694 @default.
- W2904752712 doi "https://doi.org/10.3389/fnins.2018.00913" @default.
- W2904752712 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6302114" @default.
- W2904752712 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30618549" @default.
- W2904752712 hasPublicationYear "2018" @default.
- W2904752712 type Work @default.
- W2904752712 sameAs 2904752712 @default.
- W2904752712 citedByCount "3" @default.
- W2904752712 countsByYear W29047527122021 @default.
- W2904752712 countsByYear W29047527122022 @default.
- W2904752712 crossrefType "journal-article" @default.
- W2904752712 hasAuthorship W2904752712A5010055841 @default.
- W2904752712 hasAuthorship W2904752712A5023617574 @default.
- W2904752712 hasAuthorship W2904752712A5038861361 @default.
- W2904752712 hasAuthorship W2904752712A5042414439 @default.
- W2904752712 hasBestOaLocation W29047527121 @default.
- W2904752712 hasConcept C148762608 @default.
- W2904752712 hasConcept C154945302 @default.
- W2904752712 hasConcept C169760540 @default.
- W2904752712 hasConcept C17744445 @default.
- W2904752712 hasConcept C199539241 @default.
- W2904752712 hasConcept C2776359362 @default.
- W2904752712 hasConcept C2776464000 @default.
- W2904752712 hasConcept C2778472085 @default.
- W2904752712 hasConcept C2778888523 @default.
- W2904752712 hasConcept C2779652256 @default.
- W2904752712 hasConcept C2780680797 @default.
- W2904752712 hasConcept C2992333117 @default.
- W2904752712 hasConcept C41008148 @default.