Geometric algebra model of distributed representations
From MaRDI portal
Abstract: Formalism based on GA is an alternative to distributed representation models developed so far --- Smolensky's tensor product, Holographic Reduced Representations (HRR) and Binary Spatter Code (BSC). Convolutions are replaced by geometric products, interpretable in terms of geometry which seems to be the most natural language for visualization of higher concepts. This paper recalls the main ideas behind the GA model and investigates recognition test results using both inner product and a clipped version of matrix representation. The influence of accidental blade equality on recognition is also studied. Finally, the efficiency of the GA model is compared to that of previously developed models.
Recommendations
- Distributed representations based on geometric algebra: the continuous model
- Geometric analogue of holographic reduced representation
- Experiments on preserving pieces of information in a given order in holographic reduced representations and the continuous geometric algebra model
- scientific article; zbMATH DE number 67438
- Geometric associative memories and their applications to pattern classification
Cited in
(4)- Geometric analogue of holographic reduced representation
- Mvtree for hierarchical network representation based on geometric algebra subspace
- Distributed representations based on geometric algebra: the continuous model
- Experiments on preserving pieces of information in a given order in holographic reduced representations and the continuous geometric algebra model
This page was built for publication: Geometric algebra model of distributed representations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3060696)
