Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01H0MMPZ01J8TQMZ8PMMJX73MN> ?p ?o. }
Showing items 1 to 25 of
25
with 100 items per page.
- 01H0MMPZ01J8TQMZ8PMMJX73MN classification A1.
- 01H0MMPZ01J8TQMZ8PMMJX73MN date "2023".
- 01H0MMPZ01J8TQMZ8PMMJX73MN language "eng".
- 01H0MMPZ01J8TQMZ8PMMJX73MN type journalArticle.
- 01H0MMPZ01J8TQMZ8PMMJX73MN hasPart 01H0MMRCR7AXQ6S2CX29VRD76H.pdf.
- 01H0MMPZ01J8TQMZ8PMMJX73MN hasPart 01H0MMRNS57YM34W017QTJ75ZT.pdf.
- 01H0MMPZ01J8TQMZ8PMMJX73MN subject "Technology and Engineering".
- 01H0MMPZ01J8TQMZ8PMMJX73MN doi "10.1098/rsfs.2022.0077".
- 01H0MMPZ01J8TQMZ8PMMJX73MN issn "2042-8898".
- 01H0MMPZ01J8TQMZ8PMMJX73MN issn "2042-8901".
- 01H0MMPZ01J8TQMZ8PMMJX73MN issue "3".
- 01H0MMPZ01J8TQMZ8PMMJX73MN volume "13".
- 01H0MMPZ01J8TQMZ8PMMJX73MN abstract "Humans perceive and interact with hundreds of objects every day. In doing so, they need to employ mental models of these objects and often exploit symmetries in the object's shape and appearance in order to learn generalizable and transferable skills. Active inference is a first principles approach to understanding and modelling sentient agents. It states that agents entertain a generative model of their environment, and learn and act by minimizing an upper bound on their surprisal, i.e. their free energy. The free energy decomposes into an accuracy and complexity term, meaning that agents favour the least complex model that can accurately explain their sensory observations. In this paper, we investigate how inherent symmetries of particular objects also emerge as symmetries in the latent state space of the generative model learnt under deep active inference. In particular, we focus on object-centric representations, which are trained from pixels to predict novel object views as the agent moves its viewpoint. First, we investigate the relation between model complexity and symmetry exploitation in the state space. Second, we do a principal component analysis to demonstrate how the model encodes the principal axis of symmetry of the object in the latent space. Finally, we also demonstrate how more symmetrical representations can be exploited for better generalization in the context of manipulation.".
- 01H0MMPZ01J8TQMZ8PMMJX73MN author 03627634-F0EE-11E1-A9DE-61C894A0A6B4.
- 01H0MMPZ01J8TQMZ8PMMJX73MN author 23e1a485-a7a4-11eb-b1fd-9dce8f152a2e.
- 01H0MMPZ01J8TQMZ8PMMJX73MN author AF1F6F0E-1A64-11E3-9927-3CD110BDE39D.
- 01H0MMPZ01J8TQMZ8PMMJX73MN author F4898A12-F0ED-11E1-A9DE-61C894A0A6B4.
- 01H0MMPZ01J8TQMZ8PMMJX73MN dateCreated "2023-05-17T10:39:52Z".
- 01H0MMPZ01J8TQMZ8PMMJX73MN dateModified "2024-12-12T17:54:20Z".
- 01H0MMPZ01J8TQMZ8PMMJX73MN name "Symmetry and complexity in object-centric deep active inference models".
- 01H0MMPZ01J8TQMZ8PMMJX73MN pagination urn:uuid:f428c81b-e54e-4e5e-bda5-c54401c5ac58.
- 01H0MMPZ01J8TQMZ8PMMJX73MN sameAs LU-01H0MMPZ01J8TQMZ8PMMJX73MN.
- 01H0MMPZ01J8TQMZ8PMMJX73MN sourceOrganization urn:uuid:1887c177-9f01-4f52-b3f9-948a779d3f0d.
- 01H0MMPZ01J8TQMZ8PMMJX73MN sourceOrganization urn:uuid:4f3aab5c-f1c9-44f4-a161-d745c9b81e6d.
- 01H0MMPZ01J8TQMZ8PMMJX73MN type A1.