Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288088377> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4288088377 abstract "Sensory predictions by the brain in all modalities take place as a result of bottom-up and top-down connections both in the neocortex and between the neocortex and the thalamus. The bottom-up connections in the cortex are responsible for learning, pattern recognition, and object classification, and have been widely modelled using artificial neural networks (ANNs). Here, we present a neural network architecture modelled on the top-down corticothalamic connections and the behaviour of the thalamus: a corticothalamic neural network (CTNN), consisting of an auto-encoder connected to a difference engine with a threshold. We demonstrate that the CTNN is input agnostic, multi-modal, robust during partial occlusion of one or more sensory inputs, and has significantly higher processing efficiency than other predictive coding models, proportional to the number of sequentially similar inputs in a sequence. This increased efficiency could be highly significant in more complex implementations of this architecture, where the predictive nature of the cortex will allow most of the incoming data to be discarded." @default.
- W4288088377 created "2022-07-28" @default.
- W4288088377 creator A5029625696 @default.
- W4288088377 creator A5051839290 @default.
- W4288088377 creator A5080055481 @default.
- W4288088377 date "2019-10-28" @default.
- W4288088377 modified "2023-09-30" @default.
- W4288088377 title "CTNN: Corticothalamic-inspired neural network" @default.
- W4288088377 doi "https://doi.org/10.48550/arxiv.1910.12492" @default.
- W4288088377 hasPublicationYear "2019" @default.
- W4288088377 type Work @default.
- W4288088377 citedByCount "0" @default.
- W4288088377 crossrefType "posted-content" @default.
- W4288088377 hasAuthorship W4288088377A5029625696 @default.
- W4288088377 hasAuthorship W4288088377A5051839290 @default.
- W4288088377 hasAuthorship W4288088377A5080055481 @default.
- W4288088377 hasBestOaLocation W42880883771 @default.
- W4288088377 hasConcept C153180895 @default.
- W4288088377 hasConcept C154945302 @default.
- W4288088377 hasConcept C15744967 @default.
- W4288088377 hasConcept C169760540 @default.
- W4288088377 hasConcept C2777222312 @default.
- W4288088377 hasConcept C2779246727 @default.
- W4288088377 hasConcept C41008148 @default.
- W4288088377 hasConcept C50644808 @default.
- W4288088377 hasConcept C94487597 @default.
- W4288088377 hasConceptScore W4288088377C153180895 @default.
- W4288088377 hasConceptScore W4288088377C154945302 @default.
- W4288088377 hasConceptScore W4288088377C15744967 @default.
- W4288088377 hasConceptScore W4288088377C169760540 @default.
- W4288088377 hasConceptScore W4288088377C2777222312 @default.
- W4288088377 hasConceptScore W4288088377C2779246727 @default.
- W4288088377 hasConceptScore W4288088377C41008148 @default.
- W4288088377 hasConceptScore W4288088377C50644808 @default.
- W4288088377 hasConceptScore W4288088377C94487597 @default.
- W4288088377 hasLocation W42880883771 @default.
- W4288088377 hasOpenAccess W4288088377 @default.
- W4288088377 hasPrimaryLocation W42880883771 @default.
- W4288088377 hasRelatedWork W2025969311 @default.
- W4288088377 hasRelatedWork W2059060894 @default.
- W4288088377 hasRelatedWork W2078193231 @default.
- W4288088377 hasRelatedWork W2081809247 @default.
- W4288088377 hasRelatedWork W2096777252 @default.
- W4288088377 hasRelatedWork W2114457268 @default.
- W4288088377 hasRelatedWork W2154724270 @default.
- W4288088377 hasRelatedWork W2163256521 @default.
- W4288088377 hasRelatedWork W279317441 @default.
- W4288088377 hasRelatedWork W4240758017 @default.
- W4288088377 isParatext "false" @default.
- W4288088377 isRetracted "false" @default.
- W4288088377 workType "article" @default.