Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288417961> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4288417961 abstract "The increasing need for intelligent sensors in a wide range of everyday objects requires the existence of low power information processing systems which can operate autonomously in their environment. In particular, merging and processing the outputs of different sensors efficiently is a necessary requirement for mobile agents with cognitive abilities. In this work, we present a multi-layer spiking neural network for inference of relations between stimuli patterns in dedicated neuromorphic systems. The system is trained with a new version of the backpropagation algorithm adapted to on-chip learning in neuromorphic hardware: Error gradients are encoded as spike signals which are propagated through symmetric synapses, using the same integrate-and-fire hardware infrastructure as used during forward propagation. We demonstrate the strength of the approach on an arithmetic relation inference task and on visual XOR on the MNIST dataset. Compared to previous, biologically-inspired implementations of networks for learning and inference of relations, our approach is able to achieve better performance with less neurons. Our architecture is the first spiking neural network architecture with on-chip learning capabilities, which is able to perform relational inference on complex visual stimuli. These features make our system interesting for sensor fusion applications and embedded learning in autonomous neuromorphic agents." @default.
- W4288417961 created "2022-07-29" @default.
- W4288417961 creator A5008973296 @default.
- W4288417961 creator A5052581839 @default.
- W4288417961 creator A5060241952 @default.
- W4288417961 creator A5076632990 @default.
- W4288417961 creator A5084544794 @default.
- W4288417961 date "2019-03-11" @default.
- W4288417961 modified "2023-09-26" @default.
- W4288417961 title "A Spiking Network for Inference of Relations Trained with Neuromorphic Backpropagation" @default.
- W4288417961 doi "https://doi.org/10.48550/arxiv.1903.04341" @default.
- W4288417961 hasPublicationYear "2019" @default.
- W4288417961 type Work @default.
- W4288417961 citedByCount "0" @default.
- W4288417961 crossrefType "posted-content" @default.
- W4288417961 hasAuthorship W4288417961A5008973296 @default.
- W4288417961 hasAuthorship W4288417961A5052581839 @default.
- W4288417961 hasAuthorship W4288417961A5060241952 @default.
- W4288417961 hasAuthorship W4288417961A5076632990 @default.
- W4288417961 hasAuthorship W4288417961A5084544794 @default.
- W4288417961 hasBestOaLocation W42884179611 @default.
- W4288417961 hasConcept C11731999 @default.
- W4288417961 hasConcept C118524514 @default.
- W4288417961 hasConcept C119857082 @default.
- W4288417961 hasConcept C151927369 @default.
- W4288417961 hasConcept C154945302 @default.
- W4288417961 hasConcept C155032097 @default.
- W4288417961 hasConcept C190502265 @default.
- W4288417961 hasConcept C2776214188 @default.
- W4288417961 hasConcept C41008148 @default.
- W4288417961 hasConcept C50644808 @default.
- W4288417961 hasConceptScore W4288417961C11731999 @default.
- W4288417961 hasConceptScore W4288417961C118524514 @default.
- W4288417961 hasConceptScore W4288417961C119857082 @default.
- W4288417961 hasConceptScore W4288417961C151927369 @default.
- W4288417961 hasConceptScore W4288417961C154945302 @default.
- W4288417961 hasConceptScore W4288417961C155032097 @default.
- W4288417961 hasConceptScore W4288417961C190502265 @default.
- W4288417961 hasConceptScore W4288417961C2776214188 @default.
- W4288417961 hasConceptScore W4288417961C41008148 @default.
- W4288417961 hasConceptScore W4288417961C50644808 @default.
- W4288417961 hasLocation W42884179611 @default.
- W4288417961 hasOpenAccess W4288417961 @default.
- W4288417961 hasPrimaryLocation W42884179611 @default.
- W4288417961 hasRelatedWork W2183631084 @default.
- W4288417961 hasRelatedWork W2921035465 @default.
- W4288417961 hasRelatedWork W3093460327 @default.
- W4288417961 hasRelatedWork W3117246098 @default.
- W4288417961 hasRelatedWork W3161396968 @default.
- W4288417961 hasRelatedWork W3169602696 @default.
- W4288417961 hasRelatedWork W3202412105 @default.
- W4288417961 hasRelatedWork W3214713078 @default.
- W4288417961 hasRelatedWork W4287120180 @default.
- W4288417961 hasRelatedWork W4287639722 @default.
- W4288417961 isParatext "false" @default.
- W4288417961 isRetracted "false" @default.
- W4288417961 workType "article" @default.