FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892053535> ?p ?o ?g. }

• W2892053535 endingPage "88" @default.
• W2892053535 startingPage "55" @default.
• W2892053535 abstract "Complexity is an indisputable, well-known, and broadly accepted feature of the brain. Despite the apparently obvious and widely-spread consensus on the brain complexity, sprouts of the single neuron revolution emerged in neuroscience in the 1970s. They brought many unexpected discoveries, including grandmother or concept cells and sparse coding of information in the brain. In machine learning for a long time, the famous curse of dimensionality seemed to be an unsolvable problem. Nevertheless, the idea of the blessing of dimensionality becomes gradually more and more popular. Ensembles of non-interacting or weakly interacting simple units prove to be an effective tool for solving essentially multidimensional and apparently incomprehensible problems. This approach is especially useful for one-shot (non-iterative) correction of errors in large legacy artificial intelligence systems and when the complete re-training is impossible or too expensive. These simplicity revolutions in the era of complexity have deep fundamental reasons grounded in geometry of multidimensional data spaces. To explore and understand these reasons we revisit the background ideas of statistical physics. In the course of the 20th century they were developed into the concentration of measure theory. The Gibbs equivalence of ensembles with further generalizations shows that the data in high-dimensional spaces are concentrated near shells of smaller dimension. New stochastic separation theorems reveal the fine structure of the data clouds. We review and analyse biological, physical, and mathematical problems at the core of the fundamental question: how can high-dimensional brain organise reliable and fast learning in high-dimensional world of data by simple tools? To meet this challenge, we outline and setup a framework based on statistical physics of data. Two critical applications are reviewed to exemplify the approach: one-shot correction of errors in intellectual systems and emergence of static and associative memories in ensembles of single neurons. Error correctors should be simple; not damage the existing skills of the system; allow fast non-iterative learning and correction of new mistakes without destroying the previous fixes. All these demands can be satisfied by new tools based on the concentration of measure phenomena and stochastic separation theory. We show how a simple enough functional neuronal model is capable of explaining: i) the extreme selectivity of single neurons to the information content of high-dimensional data, ii) simultaneous separation of several uncorrelated informational items from a large set of stimuli, and iii) dynamic learning of new items by associating them with already known ones. These results constitute a basis for organisation of complex memories in ensembles of single neurons." @default.
• W2892053535 created "2018-09-27" @default.
• W2892053535 creator A5035915062 @default.
• W2892053535 creator A5046235795 @default.
• W2892053535 creator A5052143104 @default.
• W2892053535 date "2019-07-01" @default.
• W2892053535 modified "2023-10-14" @default.
• W2892053535 title "The unreasonable effectiveness of small neural ensembles in high-dimensional brain" @default.
• W2892053535 cites W1503602982 @default.
• W2892053535 cites W1612304093 @default.
• W2892053535 cites W1786513448 @default.
• W2892053535 cites W1908619978 @default.
• W2892053535 cites W1969769253 @default.
• W2892053535 cites W1973286131 @default.
• W2892053535 cites W1987698418 @default.
• W2892053535 cites W1992223066 @default.
• W2892053535 cites W1998025025 @default.
• W2892053535 cites W1998050452 @default.
• W2892053535 cites W2000420612 @default.
• W2892053535 cites W2003766373 @default.
• W2892053535 cites W2013239224 @default.
• W2892053535 cites W2019639309 @default.
• W2892053535 cites W2023091089 @default.
• W2892053535 cites W2025553758 @default.
• W2892053535 cites W2027625319 @default.
• W2892053535 cites W2035238564 @default.
• W2892053535 cites W2042295339 @default.
• W2892053535 cites W2042690899 @default.
• W2892053535 cites W2047278710 @default.
• W2892053535 cites W2048812218 @default.
• W2892053535 cites W2063090026 @default.
• W2892053535 cites W2073103638 @default.
• W2892053535 cites W2074376560 @default.
• W2892053535 cites W2078176833 @default.
• W2892053535 cites W2083250197 @default.
• W2892053535 cites W2087745497 @default.
• W2892053535 cites W2091343125 @default.
• W2892053535 cites W2101295242 @default.
• W2892053535 cites W2101544483 @default.
• W2892053535 cites W2102137096 @default.
• W2892053535 cites W2102698571 @default.
• W2892053535 cites W2115990376 @default.
• W2892053535 cites W2117539524 @default.
• W2892053535 cites W2122538988 @default.
• W2892053535 cites W2123185995 @default.
• W2892053535 cites W2125138707 @default.
• W2892053535 cites W2141216438 @default.
• W2892053535 cites W2141554956 @default.
• W2892053535 cites W2141764232 @default.
• W2892053535 cites W2142925815 @default.
• W2892053535 cites W2144006746 @default.
• W2892053535 cites W2146453955 @default.
• W2892053535 cites W2152502378 @default.
• W2892053535 cites W2159475829 @default.
• W2892053535 cites W2162187012 @default.
• W2892053535 cites W2163625790 @default.
• W2892053535 cites W2172294503 @default.
• W2892053535 cites W2332352108 @default.
• W2892053535 cites W2432549741 @default.
• W2892053535 cites W2432567885 @default.
• W2892053535 cites W2527796832 @default.
• W2892053535 cites W2529292320 @default.
• W2892053535 cites W2593455419 @default.
• W2892053535 cites W2605622124 @default.
• W2892053535 cites W2791389036 @default.
• W2892053535 cites W2884716758 @default.
• W2892053535 cites W2962852687 @default.
• W2892053535 cites W2963087604 @default.
• W2892053535 cites W3037730903 @default.
• W2892053535 cites W3099661174 @default.
• W2892053535 cites W3100751155 @default.
• W2892053535 cites W4250955649 @default.
• W2892053535 doi "https://doi.org/10.1016/j.plrev.2018.09.005" @default.
• W2892053535 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30366739" @default.
• W2892053535 hasPublicationYear "2019" @default.
• W2892053535 type Work @default.
• W2892053535 sameAs 2892053535 @default.
• W2892053535 citedByCount "44" @default.
• W2892053535 countsByYear W28920535352019 @default.
• W2892053535 countsByYear W28920535352020 @default.
• W2892053535 countsByYear W28920535352021 @default.
• W2892053535 countsByYear W28920535352022 @default.
• W2892053535 countsByYear W28920535352023 @default.
• W2892053535 crossrefType "journal-article" @default.
• W2892053535 hasAuthorship W2892053535A5035915062 @default.
• W2892053535 hasAuthorship W2892053535A5046235795 @default.
• W2892053535 hasAuthorship W2892053535A5052143104 @default.
• W2892053535 hasBestOaLocation W28920535351 @default.
• W2892053535 hasConcept C111030470 @default.
• W2892053535 hasConcept C111472728 @default.
• W2892053535 hasConcept C119857082 @default.
• W2892053535 hasConcept C138885662 @default.
• W2892053535 hasConcept C154945302 @default.
• W2892053535 hasConcept C15744967 @default.
• W2892053535 hasConcept C188147891 @default.
• W2892053535 hasConcept C202444582 @default.
• W2892053535 hasConcept C2776372474 @default.
• W2892053535 hasConcept C33676613 @default.

• next