Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
- Submitting institution
-
City, University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 840
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems
- First page
- 1
- Volume
- 32
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Exception within 3 months of publication
- Month of publication
- December
- Year of publication
- 2019
- URL
-
https://papers.nips.cc/paper/8937-unsupervised-emergence-of-egocentric-spatial-structure-from-sensorimotor-prediction
- Supplementary information
-
https://papers.nips.cc/paper/2019/file/0dd1bc593a91620daecf7723d2235624-Supplemental.zip
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper appeared in NeurIPS 2019, the leading conference in AI (13000 attendees, 21.6 % acceptance rate). It proposes a novel mathematical framework that encompasses interactions and learning of agents in a physical environment. It builds on a long-lasting strand of research originating with Henri Poincare and demonstrates how agents can acquire spatial knowledge reflecting the properties of their environment through sensorimotor prediction. It relates to principles of Predictive Coding and binds insights from different scientific fields. This paper was key to the success of an EIT-digital partnership with Bosh and the financing of a PhD student.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
