Sensorimotor input as a language generalisation tool: a neurorobotics model for generation and generalisation of noun-verb combinations with sensorimotor inputs
- Submitting institution
-
Nottingham Trent University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 30 - 1118050
- Type
- D - Journal article
- DOI
-
10.1007/s10514-018-9793-7
- Title of journal
- Autonomous Robots
- Article number
- 9793
- First page
- 1271
- Volume
- 43
- Issue
- 5
- ISSN
- 0929-5593
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- 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
-
4
- Research group(s)
-
A - Computing and Informatics Research Centre
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper answered the question about how the verbs and nouns are grounded in motor actions and visual features with the same generalization behavior. Compared with previous studies, using hierarchical neural network, this model allows a humanoid robot to learn a large-scale end-to-end data-set using. The significance of this paper is that it is the first to be achieved by GPU training. This study has been followed up and published in publications in IEEE transaction TCDS ACL conferences.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
