FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007976647> ?p ?o ?g. }

• W3007976647 abstract "Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics. However, non-stationary spectral kernels are still shallow models, thus they are deficient to learn both hierarchical features and local interdependence. In this paper, to obtain hierarchical and local knowledge, we build an interpretable convolutional spectral kernel network (texttt{CSKN}) based on the inverse Fourier transform, where we introduce deep architectures and convolutional filters into non-stationary spectral kernel representations. Moreover, based on Rademacher complexity, we derive the generalization error bounds and introduce two regularizers to improve the performance. Combining the regularizers and recent advancements on random initialization, we finally complete the learning framework of texttt{CSKN}. Extensive experiments results on real-world datasets validate the effectiveness of the learning framework and coincide with our theoretical findings." @default.
• W3007976647 created "2020-03-06" @default.
• W3007976647 creator A5028071674 @default.
• W3007976647 creator A5052883326 @default.
• W3007976647 creator A5077114895 @default.
• W3007976647 date "2020-02-28" @default.
• W3007976647 modified "2023-09-23" @default.
• W3007976647 title "Convolutional Spectral Kernel Learning" @default.
• W3007976647 cites W1522301498 @default.
• W3007976647 cites W1567012231 @default.
• W3007976647 cites W1832693441 @default.
• W3007976647 cites W1944448017 @default.
• W3007976647 cites W1994906459 @default.
• W3007976647 cites W2103972604 @default.
• W3007976647 cites W2105463715 @default.
• W3007976647 cites W2106261996 @default.
• W3007976647 cites W2112796928 @default.
• W3007976647 cites W2125569215 @default.
• W3007976647 cites W2144902422 @default.
• W3007976647 cites W2153635508 @default.
• W3007976647 cites W2168464387 @default.
• W3007976647 cites W2579923771 @default.
• W3007976647 cites W2618029018 @default.
• W3007976647 cites W2753024126 @default.
• W3007976647 cites W2768793812 @default.
• W3007976647 cites W2769415053 @default.
• W3007976647 cites W2787348029 @default.
• W3007976647 cites W2809090039 @default.
• W3007976647 cites W2893252518 @default.
• W3007976647 cites W2913004909 @default.
• W3007976647 cites W2945730337 @default.
• W3007976647 cites W2949496227 @default.
• W3007976647 cites W2949578333 @default.
• W3007976647 cites W2962804662 @default.
• W3007976647 cites W2962957157 @default.
• W3007976647 cites W2963013450 @default.
• W3007976647 cites W2963063862 @default.
• W3007976647 cites W2963239103 @default.
• W3007976647 cites W2963423448 @default.
• W3007976647 cites W2963570896 @default.
• W3007976647 cites W2963626582 @default.
• W3007976647 cites W2963709899 @default.
• W3007976647 cites W2963766931 @default.
• W3007976647 cites W2963827215 @default.
• W3007976647 cites W2964050767 @default.
• W3007976647 cites W2964065616 @default.
• W3007976647 cites W2964088238 @default.
• W3007976647 cites W2966627783 @default.
• W3007976647 cites W2970330753 @default.
• W3007976647 cites W2970971581 @default.
• W3007976647 cites W2981748719 @default.
• W3007976647 cites W2997905006 @default.
• W3007976647 cites W3002335888 @default.
• W3007976647 cites W3100743579 @default.
• W3007976647 cites W3148924112 @default.
• W3007976647 cites W622188676 @default.
• W3007976647 doi "https://doi.org/10.48550/arxiv.2002.12744" @default.
• W3007976647 hasPublicationYear "2020" @default.
• W3007976647 type Work @default.
• W3007976647 sameAs 3007976647 @default.
• W3007976647 citedByCount "0" @default.
• W3007976647 crossrefType "posted-content" @default.
• W3007976647 hasAuthorship W3007976647A5028071674 @default.
• W3007976647 hasAuthorship W3007976647A5052883326 @default.
• W3007976647 hasAuthorship W3007976647A5077114895 @default.
• W3007976647 hasBestOaLocation W30079766471 @default.
• W3007976647 hasConcept C102519508 @default.
• W3007976647 hasConcept C11413529 @default.
• W3007976647 hasConcept C114466953 @default.
• W3007976647 hasConcept C118615104 @default.
• W3007976647 hasConcept C134306372 @default.
• W3007976647 hasConcept C138885662 @default.
• W3007976647 hasConcept C153180895 @default.
• W3007976647 hasConcept C154945302 @default.
• W3007976647 hasConcept C159985019 @default.
• W3007976647 hasConcept C177148314 @default.
• W3007976647 hasConcept C17744445 @default.
• W3007976647 hasConcept C192562407 @default.
• W3007976647 hasConcept C199360897 @default.
• W3007976647 hasConcept C199539241 @default.
• W3007976647 hasConcept C204323151 @default.
• W3007976647 hasConcept C207467116 @default.
• W3007976647 hasConcept C2524010 @default.
• W3007976647 hasConcept C2776359362 @default.
• W3007976647 hasConcept C2776401178 @default.
• W3007976647 hasConcept C33923547 @default.
• W3007976647 hasConcept C41008148 @default.
• W3007976647 hasConcept C41895202 @default.
• W3007976647 hasConcept C74193536 @default.
• W3007976647 hasConcept C81363708 @default.
• W3007976647 hasConcept C94625758 @default.
• W3007976647 hasConceptScore W3007976647C102519508 @default.
• W3007976647 hasConceptScore W3007976647C11413529 @default.
• W3007976647 hasConceptScore W3007976647C114466953 @default.
• W3007976647 hasConceptScore W3007976647C118615104 @default.
• W3007976647 hasConceptScore W3007976647C134306372 @default.
• W3007976647 hasConceptScore W3007976647C138885662 @default.
• W3007976647 hasConceptScore W3007976647C153180895 @default.
• W3007976647 hasConceptScore W3007976647C154945302 @default.
• W3007976647 hasConceptScore W3007976647C159985019 @default.

• next