FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387607579> ?p ?o ?g. }

• W4387607579 abstract "In recent years, with the rapid development of deep learning technology, great progress has been made in computer vision, image recognition, pattern recognition, and speech signal processing. However, due to the black-box nature of deep neural networks (DNNs), one cannot explain the parameters in the deep network and why it can perfectly perform the assigned tasks. The interpretability of neural networks has now become a research hotspot in the field of deep learning. It covers a wide range of topics in speech and text signal processing, image processing, differential equation solving, and other fields. There are subtle differences in the definition of interpretability in different fields. This paper divides interpretable neural network (INN) methods into the following two directions: model decomposition neural networks, and semantic INNs. The former mainly constructs an INN by converting the analytical model of a conventional method into different layers of neural networks and combining the interpretability of the conventional model-based method with the powerful learning capability of the neural network. This type of INNs is further classified into different subtypes depending on which type of models they are derived from, i.e., mathematical models, physical models, and other models. The second type is the interpretable network with visual semantic information for user understanding. Its basic idea is to use the visualization of the whole or partial network structure to assign semantic information to the network structure, which further includes convolutional layer output visualization, decision tree extraction, semantic graph, etc. This type of method mainly uses human visual logic to explain the structure of a black-box neural network. So it is a post-network-design method that tries to assign interpretability to a black-box network structure afterward, as opposed to the pre-network-design method of model-based INNs, which designs interpretable network structure beforehand. This paper reviews recent progress in these areas as well as various application scenarios of INNs and discusses existing problems and future development directions." @default.
• W4387607579 created "2023-10-14" @default.
• W4387607579 creator A5037106101 @default.
• W4387607579 creator A5058691076 @default.
• W4387607579 date "2023-10-13" @default.
• W4387607579 modified "2023-10-14" @default.
• W4387607579 title "Interpretable neural networks: principles and applications" @default.
• W4387607579 cites W1481776803 @default.
• W4387607579 cites W1677182931 @default.
• W4387607579 cites W1919542679 @default.
• W4387607579 cites W1978333359 @default.
• W4387607579 cites W1995341919 @default.
• W4387607579 cites W1999160507 @default.
• W4387607579 cites W2037642501 @default.
• W4387607579 cites W2048971218 @default.
• W4387607579 cites W2059746954 @default.
• W4387607579 cites W2066743741 @default.
• W4387607579 cites W2099746791 @default.
• W4387607579 cites W2100556411 @default.
• W4387607579 cites W2108598243 @default.
• W4387607579 cites W2115706991 @default.
• W4387607579 cites W2117958466 @default.
• W4387607579 cites W2147768505 @default.
• W4387607579 cites W2239232218 @default.
• W4387607579 cites W2316564661 @default.
• W4387607579 cites W2525748878 @default.
• W4387607579 cites W2560533888 @default.
• W4387607579 cites W2592696501 @default.
• W4387607579 cites W2618530766 @default.
• W4387607579 cites W2657631929 @default.
• W4387607579 cites W2749028154 @default.
• W4387607579 cites W2761490953 @default.
• W4387607579 cites W2764024122 @default.
• W4387607579 cites W2765332150 @default.
• W4387607579 cites W2769506033 @default.
• W4387607579 cites W2910683834 @default.
• W4387607579 cites W2932399282 @default.
• W4387607579 cites W2935732260 @default.
• W4387607579 cites W2949076167 @default.
• W4387607579 cites W2962772482 @default.
• W4387607579 cites W2963312584 @default.
• W4387607579 cites W2963374347 @default.
• W4387607579 cites W2963486920 @default.
• W4387607579 cites W2964030969 @default.
• W4387607579 cites W2964269625 @default.
• W4387607579 cites W2970450457 @default.
• W4387607579 cites W2972675027 @default.
• W4387607579 cites W2979997102 @default.
• W4387607579 cites W2996008180 @default.
• W4387607579 cites W2998594699 @default.
• W4387607579 cites W2998785217 @default.
• W4387607579 cites W2999026783 @default.
• W4387607579 cites W3003431099 @default.
• W4387607579 cites W3032361233 @default.
• W4387607579 cites W3032942478 @default.
• W4387607579 cites W3033137211 @default.
• W4387607579 cites W3036286896 @default.
• W4387607579 cites W3100711616 @default.
• W4387607579 cites W3107312662 @default.
• W4387607579 cites W3115079017 @default.
• W4387607579 cites W3123837026 @default.
• W4387607579 cites W3133902371 @default.
• W4387607579 cites W3135462507 @default.
• W4387607579 cites W3143107425 @default.
• W4387607579 cites W3147263230 @default.
• W4387607579 cites W3148181069 @default.
• W4387607579 cites W3154435685 @default.
• W4387607579 cites W3161200675 @default.
• W4387607579 cites W3168017910 @default.
• W4387607579 cites W3171752851 @default.
• W4387607579 cites W3176716813 @default.
• W4387607579 cites W3205922412 @default.
• W4387607579 cites W4210709750 @default.
• W4387607579 cites W4243656193 @default.
• W4387607579 cites W4281389465 @default.
• W4387607579 cites W4285276994 @default.
• W4387607579 cites W4292363360 @default.
• W4387607579 cites W4312444070 @default.
• W4387607579 doi "https://doi.org/10.3389/frai.2023.974295" @default.
• W4387607579 hasPublicationYear "2023" @default.
• W4387607579 type Work @default.
• W4387607579 citedByCount "0" @default.
• W4387607579 crossrefType "journal-article" @default.
• W4387607579 hasAuthorship W4387607579A5037106101 @default.
• W4387607579 hasAuthorship W4387607579A5058691076 @default.
• W4387607579 hasBestOaLocation W43876075791 @default.
• W4387607579 hasConcept C108583219 @default.
• W4387607579 hasConcept C119857082 @default.
• W4387607579 hasConcept C153180895 @default.
• W4387607579 hasConcept C154945302 @default.
• W4387607579 hasConcept C2781067378 @default.
• W4387607579 hasConcept C36464697 @default.
• W4387607579 hasConcept C41008148 @default.
• W4387607579 hasConcept C50644808 @default.
• W4387607579 hasConcept C81363708 @default.
• W4387607579 hasConceptScore W4387607579C108583219 @default.
• W4387607579 hasConceptScore W4387607579C119857082 @default.
• W4387607579 hasConceptScore W4387607579C153180895 @default.
• W4387607579 hasConceptScore W4387607579C154945302 @default.
• W4387607579 hasConceptScore W4387607579C2781067378 @default.

• next