FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2464471615> ?p ?o ?g. }

• W2464471615 abstract "Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage." @default.
• W2464471615 created "2016-07-22" @default.
• W2464471615 creator A5008796300 @default.
• W2464471615 creator A5027874987 @default.
• W2464471615 date "2016-07-13" @default.
• W2464471615 modified "2023-10-01" @default.
• W2464471615 title "Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions" @default.
• W2464471615 cites W1494192115 @default.
• W2464471615 cites W1540771591 @default.
• W2464471615 cites W1603307924 @default.
• W2464471615 cites W1715013381 @default.
• W2464471615 cites W1906221854 @default.
• W2464471615 cites W1917177419 @default.
• W2464471615 cites W1969806998 @default.
• W2464471615 cites W1975867390 @default.
• W2464471615 cites W1978751446 @default.
• W2464471615 cites W1985983039 @default.
• W2464471615 cites W1992007613 @default.
• W2464471615 cites W1993845689 @default.
• W2464471615 cites W1994341528 @default.
• W2464471615 cites W1997241999 @default.
• W2464471615 cites W1999653836 @default.
• W2464471615 cites W2003400208 @default.
• W2464471615 cites W2005763686 @default.
• W2464471615 cites W2007800656 @default.
• W2464471615 cites W2014766609 @default.
• W2464471615 cites W2017158895 @default.
• W2464471615 cites W2019370496 @default.
• W2464471615 cites W2024060531 @default.
• W2464471615 cites W2025192393 @default.
• W2464471615 cites W2028722600 @default.
• W2464471615 cites W2037716995 @default.
• W2464471615 cites W2039546655 @default.
• W2464471615 cites W2040036684 @default.
• W2464471615 cites W2042492924 @default.
• W2464471615 cites W2047057213 @default.
• W2464471615 cites W2051137788 @default.
• W2464471615 cites W2059787294 @default.
• W2464471615 cites W2064658612 @default.
• W2464471615 cites W2067393309 @default.
• W2464471615 cites W2077793117 @default.
• W2464471615 cites W2081498685 @default.
• W2464471615 cites W2097982135 @default.
• W2464471615 cites W2098580305 @default.
• W2464471615 cites W2100265578 @default.
• W2464471615 cites W2100495367 @default.
• W2464471615 cites W2103958039 @default.
• W2464471615 cites W2105880656 @default.
• W2464471615 cites W2108379336 @default.
• W2464471615 cites W2109616123 @default.
• W2464471615 cites W2112324576 @default.
• W2464471615 cites W2113003488 @default.
• W2464471615 cites W2113122939 @default.
• W2464471615 cites W2114174117 @default.
• W2464471615 cites W2116064496 @default.
• W2464471615 cites W2118354656 @default.
• W2464471615 cites W2119823590 @default.
• W2464471615 cites W2123713131 @default.
• W2464471615 cites W2124151298 @default.
• W2464471615 cites W2124537004 @default.
• W2464471615 cites W2124637492 @default.
• W2464471615 cites W2125663122 @default.
• W2464471615 cites W2133861842 @default.
• W2464471615 cites W2133877521 @default.
• W2464471615 cites W2133903921 @default.
• W2464471615 cites W2136435696 @default.
• W2464471615 cites W2138038826 @default.
• W2464471615 cites W2138351621 @default.
• W2464471615 cites W2139295975 @default.
• W2464471615 cites W2141047823 @default.
• W2464471615 cites W2141554956 @default.
• W2464471615 cites W2145339207 @default.
• W2464471615 cites W2148764920 @default.
• W2464471615 cites W2149565728 @default.
• W2464471615 cites W2149981795 @default.
• W2464471615 cites W2153158097 @default.
• W2464471615 cites W2153791616 @default.
• W2464471615 cites W2155477484 @default.
• W2464471615 cites W2163179684 @default.
• W2464471615 cites W2194321275 @default.
• W2464471615 cites W2257979135 @default.
• W2464471615 cites W2277170616 @default.
• W2464471615 cites W2919115771 @default.
• W2464471615 cites W4235868404 @default.
• W2464471615 cites W4238452917 @default.
• W2464471615 cites W4241759579 @default.
• W2464471615 cites W4255229883 @default.
• W2464471615 cites W4293107615 @default.
• W2464471615 cites W4300402905 @default.
• W2464471615 doi "https://doi.org/10.3389/fncom.2016.00073" @default.
• W2464471615 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/4943066" @default.
• W2464471615 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27468262" @default.
• W2464471615 hasPublicationYear "2016" @default.
• W2464471615 type Work @default.
• W2464471615 sameAs 2464471615 @default.
• W2464471615 citedByCount "39" @default.
• W2464471615 countsByYear W24644716152017 @default.
• W2464471615 countsByYear W24644716152018 @default.
• W2464471615 countsByYear W24644716152019 @default.
• W2464471615 countsByYear W24644716152020 @default.

• next