FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1815227543> ?p ?o ?g. }

• W1815227543 abstract "The neural net computer simulations which will be presented here are based on the acceptance of a set of assumptions that for the last twenty years have been expressed in the fields of information processing, neurophysiology and cognitive sciences. First of all, neural networks and their dynamical behaviors in terms of attractors is the natural way adopted by the brain to encode information. Any information item to be stored in the neural net should be coded in some way or another in one of the dynamical attractors of the brain and retrieved by stimulating the net so as to trap its dynamics in the desired item's basin of attraction. The second view shared by neural net researchers is to base the learning of the synaptic matrix on a local Hebbian mechanism. The last assumption is the presence of chaos and the benefit gained by its presence. Chaos, although very simply produced, inherently possesses an infinite amount of cyclic regimes that can be exploited for coding information. Moreover, the network randomly wanders around these unstable regimes in a spontaneous way, thus rapidly proposing alternative responses to external stimuli and being able to easily switch from one of these potential attractors to another in response to any coming stimulus.In this thesis, it is shown experimentally that the more information is to be stored in robust cyclic attractors, the more chaos appears as a regime in the back, erratically itinerating among brief appearances of these attractors. Chaos does not appear to be the cause but the consequence of the learning. However, it appears as an helpful consequence that widens the net's encoding capacity. To learn the information to be stored, an unsupervised Hebbian learning algorithm is introduced. By leaving the semantics of the attractors to be associated with the feeding data unprescribed, promising results have been obtained in term of storing capacity." @default.
• W1815227543 created "2016-06-24" @default.
• W1815227543 creator A5014677267 @default.
• W1815227543 creator A5032019511 @default.
• W1815227543 creator A5033936531 @default.
• W1815227543 date "2005-05-20" @default.
• W1815227543 modified "2023-09-23" @default.
• W1815227543 title "Storing information through complex dynamics in recurrent neural networks" @default.
• W1815227543 cites W1483579134 @default.
• W1815227543 cites W1483676554 @default.
• W1815227543 cites W1483735443 @default.
• W1815227543 cites W1492098652 @default.
• W1815227543 cites W1497673662 @default.
• W1815227543 cites W1500295349 @default.
• W1815227543 cites W1530653297 @default.
• W1815227543 cites W1534276124 @default.
• W1815227543 cites W1535810436 @default.
• W1815227543 cites W1536929369 @default.
• W1815227543 cites W1555493335 @default.
• W1815227543 cites W1580142630 @default.
• W1815227543 cites W1596839545 @default.
• W1815227543 cites W1599105596 @default.
• W1815227543 cites W1804524409 @default.
• W1815227543 cites W1943665722 @default.
• W1815227543 cites W1969071537 @default.
• W1815227543 cites W1970622727 @default.
• W1815227543 cites W1971421329 @default.
• W1815227543 cites W1973740062 @default.
• W1815227543 cites W1979684610 @default.
• W1815227543 cites W1998727969 @default.
• W1815227543 cites W1999758824 @default.
• W1815227543 cites W2004021828 @default.
• W1815227543 cites W2004274357 @default.
• W1815227543 cites W2008353316 @default.
• W1815227543 cites W2009942101 @default.
• W1815227543 cites W2016589492 @default.
• W1815227543 cites W2023877115 @default.
• W1815227543 cites W2024060531 @default.
• W1815227543 cites W2029716246 @default.
• W1815227543 cites W2029949252 @default.
• W1815227543 cites W2038168269 @default.
• W1815227543 cites W2043014754 @default.
• W1815227543 cites W2045478431 @default.
• W1815227543 cites W2048701323 @default.
• W1815227543 cites W2053463112 @default.
• W1815227543 cites W2059238825 @default.
• W1815227543 cites W2059874507 @default.
• W1815227543 cites W2069129925 @default.
• W1815227543 cites W2069586118 @default.
• W1815227543 cites W2072249973 @default.
• W1815227543 cites W2073280736 @default.
• W1815227543 cites W2074165922 @default.
• W1815227543 cites W2075510082 @default.
• W1815227543 cites W2079948225 @default.
• W1815227543 cites W2091927921 @default.
• W1815227543 cites W2094525414 @default.
• W1815227543 cites W2094639249 @default.
• W1815227543 cites W2094768061 @default.
• W1815227543 cites W2096065415 @default.
• W1815227543 cites W2103325984 @default.
• W1815227543 cites W2103463156 @default.
• W1815227543 cites W2103496339 @default.
• W1815227543 cites W2116360511 @default.
• W1815227543 cites W2124776405 @default.
• W1815227543 cites W2125331853 @default.
• W1815227543 cites W2128084896 @default.
• W1815227543 cites W2130875964 @default.
• W1815227543 cites W2133671888 @default.
• W1815227543 cites W2140681816 @default.
• W1815227543 cites W2140755429 @default.
• W1815227543 cites W2141394518 @default.
• W1815227543 cites W2144001972 @default.
• W1815227543 cites W2150355110 @default.
• W1815227543 cites W2150973855 @default.
• W1815227543 cites W2152254020 @default.
• W1815227543 cites W2157055126 @default.
• W1815227543 cites W2215343611 @default.
• W1815227543 cites W22297218 @default.
• W1815227543 cites W261458668 @default.
• W1815227543 cites W2622427009 @default.
• W1815227543 cites W3025560754 @default.
• W1815227543 cites W65738273 @default.
• W1815227543 hasPublicationYear "2005" @default.
• W1815227543 type Work @default.
• W1815227543 sameAs 1815227543 @default.
• W1815227543 citedByCount "1" @default.
• W1815227543 countsByYear W18152275432013 @default.
• W1815227543 crossrefType "proceedings-article" @default.
• W1815227543 hasAuthorship W1815227543A5014677267 @default.
• W1815227543 hasAuthorship W1815227543A5032019511 @default.
• W1815227543 hasAuthorship W1815227543A5033936531 @default.
• W1815227543 hasConcept C104317684 @default.
• W1815227543 hasConcept C111437709 @default.
• W1815227543 hasConcept C118615104 @default.
• W1815227543 hasConcept C121332964 @default.
• W1815227543 hasConcept C121864883 @default.
• W1815227543 hasConcept C123757187 @default.
• W1815227543 hasConcept C134306372 @default.
• W1815227543 hasConcept C152478114 @default.
• W1815227543 hasConcept C154945302 @default.

• next