FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092016148> ?p ?o ?g. }

• W3092016148 abstract "We propose a few-shot learning method for spatial regression. Although Gaussian processes (GPs) have been successfully used for spatial regression, they require many observations in the target task to achieve a high predictive performance. Our model is trained using spatial datasets on various attributes in various regions, and predicts values on unseen attributes in unseen regions given a few observed data. With our model, a task representation is inferred from given small data using a neural network. Then, spatial values are predicted by neural networks with a GP framework, in which task-specific properties are controlled by the task representations. The GP framework allows us to analytically obtain predictions that are adapted to small data. By using the adapted predictions in the objective function, we can train our model efficiently and effectively so that the test predictive performance improves when adapted to newly given small data. In our experiments, we demonstrate that the proposed method achieves better predictive performance than existing meta-learning methods using spatial datasets." @default.
• W3092016148 created "2020-10-15" @default.
• W3092016148 creator A5000602137 @default.
• W3092016148 creator A5034538103 @default.
• W3092016148 date "2020-10-09" @default.
• W3092016148 modified "2023-10-16" @default.
• W3092016148 title "Few-shot Learning for Spatial Regression" @default.
• W3092016148 cites W1746819321 @default.
• W3092016148 cites W1870250857 @default.
• W3092016148 cites W1970679066 @default.
• W3092016148 cites W1978056375 @default.
• W3092016148 cites W2004807582 @default.
• W3092016148 cites W2019597798 @default.
• W3092016148 cites W2061163110 @default.
• W3092016148 cites W2067960722 @default.
• W3092016148 cites W2068695859 @default.
• W3092016148 cites W2074984119 @default.
• W3092016148 cites W2075364600 @default.
• W3092016148 cites W2081496546 @default.
• W3092016148 cites W2090636204 @default.
• W3092016148 cites W2096812863 @default.
• W3092016148 cites W2108495858 @default.
• W3092016148 cites W2112738128 @default.
• W3092016148 cites W2114735331 @default.
• W3092016148 cites W2119595900 @default.
• W3092016148 cites W2120626248 @default.
• W3092016148 cites W2123399796 @default.
• W3092016148 cites W2128338591 @default.
• W3092016148 cites W2148522164 @default.
• W3092016148 cites W2150552259 @default.
• W3092016148 cites W2153207204 @default.
• W3092016148 cites W2168464387 @default.
• W3092016148 cites W2182365035 @default.
• W3092016148 cites W2251230758 @default.
• W3092016148 cites W2298457129 @default.
• W3092016148 cites W2316627393 @default.
• W3092016148 cites W2411334469 @default.
• W3092016148 cites W2412589713 @default.
• W3092016148 cites W2472819217 @default.
• W3092016148 cites W2514525802 @default.
• W3092016148 cites W2549019841 @default.
• W3092016148 cites W2601450892 @default.
• W3092016148 cites W2604763608 @default.
• W3092016148 cites W2739429571 @default.
• W3092016148 cites W2741826335 @default.
• W3092016148 cites W2742093937 @default.
• W3092016148 cites W2753160622 @default.
• W3092016148 cites W2753798143 @default.
• W3092016148 cites W2766669584 @default.
• W3092016148 cites W2785902771 @default.
• W3092016148 cites W2799251726 @default.
• W3092016148 cites W2883670420 @default.
• W3092016148 cites W2899771611 @default.
• W3092016148 cites W2913243980 @default.
• W3092016148 cites W2946757877 @default.
• W3092016148 cites W2947341830 @default.
• W3092016148 cites W2951249948 @default.
• W3092016148 cites W2962908092 @default.
• W3092016148 cites W2963070905 @default.
• W3092016148 cites W2963221401 @default.
• W3092016148 cites W2963341924 @default.
• W3092016148 cites W2963557251 @default.
• W3092016148 cites W2963775850 @default.
• W3092016148 cites W2964078140 @default.
• W3092016148 cites W2964112702 @default.
• W3092016148 cites W2964121744 @default.
• W3092016148 cites W2964121937 @default.
• W3092016148 cites W2964135722 @default.
• W3092016148 cites W2964206659 @default.
• W3092016148 cites W2973341869 @default.
• W3092016148 cites W2978409868 @default.
• W3092016148 cites W2981368934 @default.
• W3092016148 cites W3005836185 @default.
• W3092016148 doi "https://doi.org/10.48550/arxiv.2010.04360" @default.
• W3092016148 hasPublicationYear "2020" @default.
• W3092016148 type Work @default.
• W3092016148 sameAs 3092016148 @default.
• W3092016148 citedByCount "2" @default.
• W3092016148 countsByYear W30920161482021 @default.
• W3092016148 crossrefType "posted-content" @default.
• W3092016148 hasAuthorship W3092016148A5000602137 @default.
• W3092016148 hasAuthorship W3092016148A5034538103 @default.
• W3092016148 hasBestOaLocation W30920161481 @default.
• W3092016148 hasConcept C105795698 @default.
• W3092016148 hasConcept C119857082 @default.
• W3092016148 hasConcept C121332964 @default.
• W3092016148 hasConcept C124101348 @default.
• W3092016148 hasConcept C153180895 @default.
• W3092016148 hasConcept C154945302 @default.
• W3092016148 hasConcept C159620131 @default.
• W3092016148 hasConcept C162324750 @default.
• W3092016148 hasConcept C163716315 @default.
• W3092016148 hasConcept C17744445 @default.
• W3092016148 hasConcept C187736073 @default.
• W3092016148 hasConcept C199539241 @default.
• W3092016148 hasConcept C2776359362 @default.
• W3092016148 hasConcept C2780451532 @default.
• W3092016148 hasConcept C33923547 @default.
• W3092016148 hasConcept C41008148 @default.
• W3092016148 hasConcept C50644808 @default.

• next