Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309130123> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4309130123 abstract "Imitation learning allows social robots to learn new skills from human teachers without substantial manual programming, but it is difficult for robotic imitation learning systems to generalize demonstrated skills as well as human learners do. Contemporary neurocomputational approaches to imitation learning achieve limited generalization at the cost of data-intensive training, and often produce opaque models that are difficult to understand and debug. In this study, we explore the viability of developing purely-neural controllers for social robots that learn to imitate by reasoning about the underlying intentions of demonstrated behaviors. We present NeuroCERIL, a brain-inspired neurocognitive architecture that uses a novel hypothetico-deductive reasoning procedure to produce generalizable and human-readable explanations for demonstrated behavior. This approach combines bottom-up abductive inference with top-down predictive verification, and captures important aspects of human causal reasoning that are relevant to a broad range of cognitive domains. Our empirical results demonstrate that NeuroCERIL can learn various procedural skills in a simulated robotic imitation learning domain. We also show that its causal reasoning procedure is computationally efficient, and that its memory use is dominated by highly transient short-term memories, much like human working memory. We conclude that NeuroCERIL is a viable neural model of human-like imitation learning that can improve human-robot collaboration and contribute to investigations of the neurocomputational basis of human cognition." @default.
- W4309130123 created "2022-11-23" @default.
- W4309130123 creator A5045810696 @default.
- W4309130123 creator A5050009555 @default.
- W4309130123 creator A5051693199 @default.
- W4309130123 creator A5076437195 @default.
- W4309130123 date "2022-11-11" @default.
- W4309130123 modified "2023-10-14" @default.
- W4309130123 title "NeuroCERIL: Robotic Imitation Learning via Hierarchical Cause-Effect Reasoning in Programmable Attractor Neural Networks" @default.
- W4309130123 doi "https://doi.org/10.48550/arxiv.2211.06462" @default.
- W4309130123 hasPublicationYear "2022" @default.
- W4309130123 type Work @default.
- W4309130123 citedByCount "0" @default.
- W4309130123 crossrefType "posted-content" @default.
- W4309130123 hasAuthorship W4309130123A5045810696 @default.
- W4309130123 hasAuthorship W4309130123A5050009555 @default.
- W4309130123 hasAuthorship W4309130123A5051693199 @default.
- W4309130123 hasAuthorship W4309130123A5076437195 @default.
- W4309130123 hasBestOaLocation W43091301231 @default.
- W4309130123 hasConcept C119857082 @default.
- W4309130123 hasConcept C126388530 @default.
- W4309130123 hasConcept C134306372 @default.
- W4309130123 hasConcept C154945302 @default.
- W4309130123 hasConcept C15744967 @default.
- W4309130123 hasConcept C169760540 @default.
- W4309130123 hasConcept C169900460 @default.
- W4309130123 hasConcept C177148314 @default.
- W4309130123 hasConcept C188147891 @default.
- W4309130123 hasConcept C192327766 @default.
- W4309130123 hasConcept C20854674 @default.
- W4309130123 hasConcept C2776214188 @default.
- W4309130123 hasConcept C33923547 @default.
- W4309130123 hasConcept C41008148 @default.
- W4309130123 hasConcept C77805123 @default.
- W4309130123 hasConcept C90509273 @default.
- W4309130123 hasConceptScore W4309130123C119857082 @default.
- W4309130123 hasConceptScore W4309130123C126388530 @default.
- W4309130123 hasConceptScore W4309130123C134306372 @default.
- W4309130123 hasConceptScore W4309130123C154945302 @default.
- W4309130123 hasConceptScore W4309130123C15744967 @default.
- W4309130123 hasConceptScore W4309130123C169760540 @default.
- W4309130123 hasConceptScore W4309130123C169900460 @default.
- W4309130123 hasConceptScore W4309130123C177148314 @default.
- W4309130123 hasConceptScore W4309130123C188147891 @default.
- W4309130123 hasConceptScore W4309130123C192327766 @default.
- W4309130123 hasConceptScore W4309130123C20854674 @default.
- W4309130123 hasConceptScore W4309130123C2776214188 @default.
- W4309130123 hasConceptScore W4309130123C33923547 @default.
- W4309130123 hasConceptScore W4309130123C41008148 @default.
- W4309130123 hasConceptScore W4309130123C77805123 @default.
- W4309130123 hasConceptScore W4309130123C90509273 @default.
- W4309130123 hasLocation W43091301231 @default.
- W4309130123 hasLocation W43091301232 @default.
- W4309130123 hasOpenAccess W4309130123 @default.
- W4309130123 hasPrimaryLocation W43091301231 @default.
- W4309130123 hasRelatedWork W140699112 @default.
- W4309130123 hasRelatedWork W1595924246 @default.
- W4309130123 hasRelatedWork W168624679 @default.
- W4309130123 hasRelatedWork W2134748080 @default.
- W4309130123 hasRelatedWork W2183362005 @default.
- W4309130123 hasRelatedWork W2403045559 @default.
- W4309130123 hasRelatedWork W2623253978 @default.
- W4309130123 hasRelatedWork W2773734151 @default.
- W4309130123 hasRelatedWork W2891970620 @default.
- W4309130123 hasRelatedWork W586545757 @default.
- W4309130123 isParatext "false" @default.
- W4309130123 isRetracted "false" @default.
- W4309130123 workType "article" @default.