Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203502785> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3203502785 endingPage "1284" @default.
- W3203502785 startingPage "1276" @default.
- W3203502785 abstract "Solving geometric tasks using machine learning is a challenging problem. Standard feed-forward neural networks combine linear or, if the bias parameter is included, affine layers and activation functions. Their geometric modeling is limited, which is why we introduce the alternative model of the multilayer geometric perceptron (MLGP) with units that are geometric neurons, i.e., combinations of hypersphere neurons. The hypersphere neuron is obtained by applying a conformal embedding of Euclidean space. By virtue of Clifford algebra, it can be implemented as the Cartesian dot product. We validate our method on the public 3D Tetris dataset consisting of coordinates of geometric shapes and we show that our method has the capability of generalization over geometric transformations. We demonstrate that our model is superior to the vanilla multilayer perceptron (MLP) while having fewer parameters and no activation function in the hidden layers other than the embedding. In the presence of noise in the data, our model is also superior to the multilayer hypersphere perceptron (MLHP) proposed in prior work. In contrast to the latter, our method reflects the 3D-geometry and provides a topological interpretation of the learned coefficients in the geometric neurons." @default.
- W3203502785 created "2021-10-11" @default.
- W3203502785 creator A5042087981 @default.
- W3203502785 creator A5052501521 @default.
- W3203502785 creator A5077434694 @default.
- W3203502785 date "2020-06-11" @default.
- W3203502785 modified "2023-09-24" @default.
- W3203502785 title "Embed Me If You Can: A Geometric Perceptron" @default.
- W3203502785 hasPublicationYear "2020" @default.
- W3203502785 type Work @default.
- W3203502785 sameAs 3203502785 @default.
- W3203502785 citedByCount "1" @default.
- W3203502785 countsByYear W32035027852021 @default.
- W3203502785 crossrefType "proceedings-article" @default.
- W3203502785 hasAuthorship W3203502785A5042087981 @default.
- W3203502785 hasAuthorship W3203502785A5052501521 @default.
- W3203502785 hasAuthorship W3203502785A5077434694 @default.
- W3203502785 hasConcept C100856211 @default.
- W3203502785 hasConcept C11413529 @default.
- W3203502785 hasConcept C134306372 @default.
- W3203502785 hasConcept C136119220 @default.
- W3203502785 hasConcept C147898140 @default.
- W3203502785 hasConcept C153180895 @default.
- W3203502785 hasConcept C154945302 @default.
- W3203502785 hasConcept C177148314 @default.
- W3203502785 hasConcept C180671464 @default.
- W3203502785 hasConcept C186450821 @default.
- W3203502785 hasConcept C202444582 @default.
- W3203502785 hasConcept C2524010 @default.
- W3203502785 hasConcept C2776562905 @default.
- W3203502785 hasConcept C33923547 @default.
- W3203502785 hasConcept C41008148 @default.
- W3203502785 hasConcept C41608201 @default.
- W3203502785 hasConcept C50644808 @default.
- W3203502785 hasConcept C92757383 @default.
- W3203502785 hasConcept C98214594 @default.
- W3203502785 hasConceptScore W3203502785C100856211 @default.
- W3203502785 hasConceptScore W3203502785C11413529 @default.
- W3203502785 hasConceptScore W3203502785C134306372 @default.
- W3203502785 hasConceptScore W3203502785C136119220 @default.
- W3203502785 hasConceptScore W3203502785C147898140 @default.
- W3203502785 hasConceptScore W3203502785C153180895 @default.
- W3203502785 hasConceptScore W3203502785C154945302 @default.
- W3203502785 hasConceptScore W3203502785C177148314 @default.
- W3203502785 hasConceptScore W3203502785C180671464 @default.
- W3203502785 hasConceptScore W3203502785C186450821 @default.
- W3203502785 hasConceptScore W3203502785C202444582 @default.
- W3203502785 hasConceptScore W3203502785C2524010 @default.
- W3203502785 hasConceptScore W3203502785C2776562905 @default.
- W3203502785 hasConceptScore W3203502785C33923547 @default.
- W3203502785 hasConceptScore W3203502785C41008148 @default.
- W3203502785 hasConceptScore W3203502785C41608201 @default.
- W3203502785 hasConceptScore W3203502785C50644808 @default.
- W3203502785 hasConceptScore W3203502785C92757383 @default.
- W3203502785 hasConceptScore W3203502785C98214594 @default.
- W3203502785 hasLocation W32035027851 @default.
- W3203502785 hasOpenAccess W3203502785 @default.
- W3203502785 hasPrimaryLocation W32035027851 @default.
- W3203502785 hasRelatedWork W1529647383 @default.
- W3203502785 hasRelatedWork W1576721967 @default.
- W3203502785 hasRelatedWork W1577661154 @default.
- W3203502785 hasRelatedWork W1980906795 @default.
- W3203502785 hasRelatedWork W2018212615 @default.
- W3203502785 hasRelatedWork W202675831 @default.
- W3203502785 hasRelatedWork W2076029078 @default.
- W3203502785 hasRelatedWork W2133358562 @default.
- W3203502785 hasRelatedWork W2143350754 @default.
- W3203502785 hasRelatedWork W2152424459 @default.
- W3203502785 hasRelatedWork W2158720754 @default.
- W3203502785 hasRelatedWork W2477865973 @default.
- W3203502785 hasRelatedWork W2735962926 @default.
- W3203502785 hasRelatedWork W2804606950 @default.
- W3203502785 hasRelatedWork W2912029373 @default.
- W3203502785 hasRelatedWork W3034519114 @default.
- W3203502785 hasRelatedWork W3045370061 @default.
- W3203502785 hasRelatedWork W3100852746 @default.
- W3203502785 hasRelatedWork W3140685987 @default.
- W3203502785 hasRelatedWork W326490330 @default.
- W3203502785 isParatext "false" @default.
- W3203502785 isRetracted "false" @default.
- W3203502785 magId "3203502785" @default.
- W3203502785 workType "article" @default.