Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226182406> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4226182406 abstract "Kernel based Deep Learning using multi-layer kernel machines(MKMs) was proposed by Y.Cho and L.K. Saul in cite{saul}. In MKMs they used only one kernel(arc-cosine kernel) at a layer for the kernel PCA-based feature extraction. We propose to use multiple kernels in each layer by taking a convex combination of many kernels following an unsupervised learning strategy. Empirical study is conducted on textit{mnist-back-rand}, textit{mnist-back-image} and textit{mnist-rot-back-image} datasets generated by adding random noise in the image background of MNIST dataset. Experimental results indicate that using MKL in MKMs earns a better representation of the raw data and improves the classifier performance." @default.
- W4226182406 created "2022-05-05" @default.
- W4226182406 creator A5020412774 @default.
- W4226182406 creator A5042656485 @default.
- W4226182406 creator A5054101231 @default.
- W4226182406 date "2021-11-26" @default.
- W4226182406 modified "2023-09-28" @default.
- W4226182406 title "Unsupervised MKL in Multi-layer Kernel Machines" @default.
- W4226182406 hasPublicationYear "2021" @default.
- W4226182406 type Work @default.
- W4226182406 citedByCount "0" @default.
- W4226182406 crossrefType "posted-content" @default.
- W4226182406 hasAuthorship W4226182406A5020412774 @default.
- W4226182406 hasAuthorship W4226182406A5042656485 @default.
- W4226182406 hasAuthorship W4226182406A5054101231 @default.
- W4226182406 hasBestOaLocation W42261824061 @default.
- W4226182406 hasConcept C108583219 @default.
- W4226182406 hasConcept C114614502 @default.
- W4226182406 hasConcept C122280245 @default.
- W4226182406 hasConcept C12267149 @default.
- W4226182406 hasConcept C153180895 @default.
- W4226182406 hasConcept C154945302 @default.
- W4226182406 hasConcept C190502265 @default.
- W4226182406 hasConcept C2776879701 @default.
- W4226182406 hasConcept C33923547 @default.
- W4226182406 hasConcept C41008148 @default.
- W4226182406 hasConcept C74193536 @default.
- W4226182406 hasConcept C75866337 @default.
- W4226182406 hasConcept C95623464 @default.
- W4226182406 hasConceptScore W4226182406C108583219 @default.
- W4226182406 hasConceptScore W4226182406C114614502 @default.
- W4226182406 hasConceptScore W4226182406C122280245 @default.
- W4226182406 hasConceptScore W4226182406C12267149 @default.
- W4226182406 hasConceptScore W4226182406C153180895 @default.
- W4226182406 hasConceptScore W4226182406C154945302 @default.
- W4226182406 hasConceptScore W4226182406C190502265 @default.
- W4226182406 hasConceptScore W4226182406C2776879701 @default.
- W4226182406 hasConceptScore W4226182406C33923547 @default.
- W4226182406 hasConceptScore W4226182406C41008148 @default.
- W4226182406 hasConceptScore W4226182406C74193536 @default.
- W4226182406 hasConceptScore W4226182406C75866337 @default.
- W4226182406 hasConceptScore W4226182406C95623464 @default.
- W4226182406 hasLocation W42261824061 @default.
- W4226182406 hasOpenAccess W4226182406 @default.
- W4226182406 hasPrimaryLocation W42261824061 @default.
- W4226182406 hasRelatedWork W10267022 @default.
- W4226182406 hasRelatedWork W10931660 @default.
- W4226182406 hasRelatedWork W1368183 @default.
- W4226182406 hasRelatedWork W13771663 @default.
- W4226182406 hasRelatedWork W15962362 @default.
- W4226182406 hasRelatedWork W5114324 @default.
- W4226182406 hasRelatedWork W5557673 @default.
- W4226182406 hasRelatedWork W62477 @default.
- W4226182406 hasRelatedWork W6717794 @default.
- W4226182406 hasRelatedWork W7294302 @default.
- W4226182406 isParatext "false" @default.
- W4226182406 isRetracted "false" @default.
- W4226182406 workType "article" @default.