FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2294916050> ?p ?o ?g. }

• W2294916050 endingPage "439" @default.
• W2294916050 startingPage "427" @default.
• W2294916050 abstract "In this paper, we elaborate over the well-known interpretability issue in echo state networks. The idea is to investigate the dynamics of reservoir neurons with time-series analysis techniques taken from research on complex systems. Notably, we analyze time-series of neuron activations with Recurrence Plots (RPs) and Recurrence Quantification Analysis (RQA), which permit to visualize and characterize high-dimensional dynamical systems. We show that this approach is useful in a number of ways. First, the two-dimensional representation offered by RPs provides a way for visualizing the high-dimensional dynamics of a reservoir. Our results suggest that, if the network is stable, reservoir and input denote similar line patterns in the respective RPs. Conversely, the more unstable the ESN, the more the RP of the reservoir presents instability patterns. As a second result, we show that the $mathrm{L_{max}}$ measure is highly correlated with the well-established maximal local Lyapunov exponent. This suggests that complexity measures based on RP diagonal lines distribution provide a valuable tool to quantify the degree of network stability. Finally, our analysis shows that all RQA measures fluctuate on the proximity of the so-called edge of stability, where an ESN typically achieves maximum computational capability. We verify that the determination of the edge of stability provided by such RQA measures is more accurate than two well-known criteria based on the Jacobian matrix of the reservoir. Therefore, we claim that RPs and RQA-based analyses can be used as valuable tools to design an effective network given a specific problem." @default.
• W2294916050 created "2016-06-24" @default.
• W2294916050 creator A5005003786 @default.
• W2294916050 creator A5036254733 @default.
• W2294916050 creator A5078445362 @default.
• W2294916050 date "2018-02-01" @default.
• W2294916050 modified "2023-09-27" @default.
• W2294916050 title "Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis" @default.
• W2294916050 cites W1501306604 @default.
• W2294916050 cites W1542602301 @default.
• W2294916050 cites W1544900599 @default.
• W2294916050 cites W1908962573 @default.
• W2294916050 cites W1977664984 @default.
• W2294916050 cites W1978845507 @default.
• W2294916050 cites W1980324747 @default.
• W2294916050 cites W1981510969 @default.
• W2294916050 cites W1984516841 @default.
• W2294916050 cites W1987299193 @default.
• W2294916050 cites W1989312953 @default.
• W2294916050 cites W2003627696 @default.
• W2294916050 cites W2021379535 @default.
• W2294916050 cites W2022175477 @default.
• W2294916050 cites W2027465564 @default.
• W2294916050 cites W2029967456 @default.
• W2294916050 cites W2036451492 @default.
• W2294916050 cites W2042489792 @default.
• W2294916050 cites W2046509362 @default.
• W2294916050 cites W2048694956 @default.
• W2294916050 cites W2050142243 @default.
• W2294916050 cites W2050592754 @default.
• W2294916050 cites W2057755457 @default.
• W2294916050 cites W2058953281 @default.
• W2294916050 cites W2060483994 @default.
• W2294916050 cites W2079329690 @default.
• W2294916050 cites W2081681829 @default.
• W2294916050 cites W2089138141 @default.
• W2294916050 cites W2102385858 @default.
• W2294916050 cites W2118706537 @default.
• W2294916050 cites W2125091774 @default.
• W2294916050 cites W2125790506 @default.
• W2294916050 cites W2128171517 @default.
• W2294916050 cites W2131619958 @default.
• W2294916050 cites W2134603460 @default.
• W2294916050 cites W2139287577 @default.
• W2294916050 cites W2148520247 @default.
• W2294916050 cites W2152361984 @default.
• W2294916050 cites W2159682675 @default.
• W2294916050 cites W2165150869 @default.
• W2294916050 cites W2171865010 @default.
• W2294916050 cites W2177218873 @default.
• W2294916050 cites W3102171169 @default.
• W2294916050 cites W3105276629 @default.
• W2294916050 doi "https://doi.org/10.1109/tnnls.2016.2630802" @default.
• W2294916050 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28114039" @default.
• W2294916050 hasPublicationYear "2018" @default.
• W2294916050 type Work @default.
• W2294916050 sameAs 2294916050 @default.
• W2294916050 citedByCount "76" @default.
• W2294916050 countsByYear W22949160502017 @default.
• W2294916050 countsByYear W22949160502018 @default.
• W2294916050 countsByYear W22949160502019 @default.
• W2294916050 countsByYear W22949160502020 @default.
• W2294916050 countsByYear W22949160502021 @default.
• W2294916050 countsByYear W22949160502022 @default.
• W2294916050 countsByYear W22949160502023 @default.
• W2294916050 crossrefType "journal-article" @default.
• W2294916050 hasAuthorship W2294916050A5005003786 @default.
• W2294916050 hasAuthorship W2294916050A5036254733 @default.
• W2294916050 hasAuthorship W2294916050A5078445362 @default.
• W2294916050 hasBestOaLocation W22949160502 @default.
• W2294916050 hasConcept C112972136 @default.
• W2294916050 hasConcept C119857082 @default.
• W2294916050 hasConcept C121332964 @default.
• W2294916050 hasConcept C121864883 @default.
• W2294916050 hasConcept C130367717 @default.
• W2294916050 hasConcept C143724316 @default.
• W2294916050 hasConcept C147168706 @default.
• W2294916050 hasConcept C151730666 @default.
• W2294916050 hasConcept C154945302 @default.
• W2294916050 hasConcept C158622935 @default.
• W2294916050 hasConcept C172025690 @default.
• W2294916050 hasConcept C173134143 @default.
• W2294916050 hasConcept C17744445 @default.
• W2294916050 hasConcept C191544260 @default.
• W2294916050 hasConcept C199539241 @default.
• W2294916050 hasConcept C200331156 @default.
• W2294916050 hasConcept C2524010 @default.
• W2294916050 hasConcept C2776359362 @default.
• W2294916050 hasConcept C2777052490 @default.
• W2294916050 hasConcept C2781067378 @default.
• W2294916050 hasConcept C28826006 @default.
• W2294916050 hasConcept C33923547 @default.
• W2294916050 hasConcept C41008148 @default.
• W2294916050 hasConcept C43456602 @default.
• W2294916050 hasConcept C47822265 @default.
• W2294916050 hasConcept C50644808 @default.
• W2294916050 hasConcept C62520636 @default.
• W2294916050 hasConcept C86803240 @default.

• next