FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W962941314> ?p ?o ?g. }

• W962941314 abstract "During the past decade, a new class of knowledge representation has emerged known as structured distributed representation (SDR). A number of schemes for encoding and manipulating such representations have been developed; e.g. Pollack’s Recursive Auto-Associative Memory (RAAM), Kanerva’s Binary Spatter Code (BSC), Gayler’s MAP encoding, and Plate’s Holographically Reduced Representations (HRR). All such schemes encode structural information throughout the elements of high dimensional vectors, and are manipulated with rudimentary algebraic operations. Most SDRs are very compact; components and compositions of components are all represented as fixed-width vectors. However, such compact compositions are unavoidably noisy. As a result, resolving constituent components requires a cleanup memory. In its simplest form, cleanup is performed with a list of vectors that are sequentially compared using a similarity metric. The closest match is deemed the cleaned codevector. While SDR schemes were originally designed to perform cognitive tasks, none of them have been demonstrated in a neurobiologically plausible substrate. Potentially, mathematically proven properties of these systems may not be neurally realistic. Using Eliasmith and Anderson’s 2003 Neural Engineering Framework, I construct various spiking neural networks to simulate a general cleanup memory that is suitable for many schemes. Importantly, previous work has not taken advantage of parallelization or the high-dimensional properties of neural networks. Nor have they considered the efiii fect of noise within these systems. As well, additional improvements to the cleanup operation may be possible by more efficiently structuring the memory itself. In this thesis I address these lacuna, provide an analysis of systems accuracy, capacity, scalability, and robustness to noise, and explore ways to improve the search efficiency." @default.
• W962941314 created "2016-06-24" @default.
• W962941314 creator A5035796584 @default.
• W962941314 date "2005-01-01" @default.
• W962941314 modified "2023-09-26" @default.
• W962941314 title "Cleanup Memory in Biologically Plausible Neural Networks" @default.
• W962941314 cites W1486060514 @default.
• W962941314 cites W1486735428 @default.
• W962941314 cites W1486990335 @default.
• W962941314 cites W1488378957 @default.
• W962941314 cites W1519151035 @default.
• W962941314 cites W1528406203 @default.
• W962941314 cites W1539686131 @default.
• W962941314 cites W1573706465 @default.
• W962941314 cites W1589549454 @default.
• W962941314 cites W1634005169 @default.
• W962941314 cites W1943478593 @default.
• W962941314 cites W1954464791 @default.
• W962941314 cites W1968079292 @default.
• W962941314 cites W1971844566 @default.
• W962941314 cites W2009784500 @default.
• W962941314 cites W2013494846 @default.
• W962941314 cites W2026675255 @default.
• W962941314 cites W2032927127 @default.
• W962941314 cites W2040739363 @default.
• W962941314 cites W2061278547 @default.
• W962941314 cites W2065077271 @default.
• W962941314 cites W2074376560 @default.
• W962941314 cites W2075665712 @default.
• W962941314 cites W2085113259 @default.
• W962941314 cites W2104436836 @default.
• W962941314 cites W2118150858 @default.
• W962941314 cites W2142248489 @default.
• W962941314 cites W2150161574 @default.
• W962941314 cites W2157306293 @default.
• W962941314 cites W2339502089 @default.
• W962941314 cites W2912565176 @default.
• W962941314 cites W639309485 @default.
• W962941314 cites W83940682 @default.
• W962941314 cites W89291759 @default.
• W962941314 hasPublicationYear "2005" @default.
• W962941314 type Work @default.
• W962941314 sameAs 962941314 @default.
• W962941314 citedByCount "0" @default.
• W962941314 crossrefType "dissertation" @default.
• W962941314 hasAuthorship W962941314A5035796584 @default.
• W962941314 hasConcept C10138342 @default.
• W962941314 hasConcept C104317684 @default.
• W962941314 hasConcept C120620853 @default.
• W962941314 hasConcept C125411270 @default.
• W962941314 hasConcept C134306372 @default.
• W962941314 hasConcept C136003732 @default.
• W962941314 hasConcept C154945302 @default.
• W962941314 hasConcept C159423971 @default.
• W962941314 hasConcept C162324750 @default.
• W962941314 hasConcept C177264268 @default.
• W962941314 hasConcept C17744445 @default.
• W962941314 hasConcept C185592680 @default.
• W962941314 hasConcept C199360897 @default.
• W962941314 hasConcept C199539241 @default.
• W962941314 hasConcept C202444582 @default.
• W962941314 hasConcept C2775945657 @default.
• W962941314 hasConcept C2776359362 @default.
• W962941314 hasConcept C2776760102 @default.
• W962941314 hasConcept C2780801425 @default.
• W962941314 hasConcept C33923547 @default.
• W962941314 hasConcept C41008148 @default.
• W962941314 hasConcept C48372109 @default.
• W962941314 hasConcept C50644808 @default.
• W962941314 hasConcept C53442348 @default.
• W962941314 hasConcept C55493867 @default.
• W962941314 hasConcept C66746571 @default.
• W962941314 hasConcept C80444323 @default.
• W962941314 hasConcept C9376300 @default.
• W962941314 hasConcept C94375191 @default.
• W962941314 hasConcept C94625758 @default.
• W962941314 hasConceptScore W962941314C10138342 @default.
• W962941314 hasConceptScore W962941314C104317684 @default.
• W962941314 hasConceptScore W962941314C120620853 @default.
• W962941314 hasConceptScore W962941314C125411270 @default.
• W962941314 hasConceptScore W962941314C134306372 @default.
• W962941314 hasConceptScore W962941314C136003732 @default.
• W962941314 hasConceptScore W962941314C154945302 @default.
• W962941314 hasConceptScore W962941314C159423971 @default.
• W962941314 hasConceptScore W962941314C162324750 @default.
• W962941314 hasConceptScore W962941314C177264268 @default.
• W962941314 hasConceptScore W962941314C17744445 @default.
• W962941314 hasConceptScore W962941314C185592680 @default.
• W962941314 hasConceptScore W962941314C199360897 @default.
• W962941314 hasConceptScore W962941314C199539241 @default.
• W962941314 hasConceptScore W962941314C202444582 @default.
• W962941314 hasConceptScore W962941314C2775945657 @default.
• W962941314 hasConceptScore W962941314C2776359362 @default.
• W962941314 hasConceptScore W962941314C2776760102 @default.
• W962941314 hasConceptScore W962941314C2780801425 @default.
• W962941314 hasConceptScore W962941314C33923547 @default.
• W962941314 hasConceptScore W962941314C41008148 @default.
• W962941314 hasConceptScore W962941314C48372109 @default.
• W962941314 hasConceptScore W962941314C50644808 @default.
• W962941314 hasConceptScore W962941314C53442348 @default.

• next