Chater, N. and Oaksford, Mike (2017) Theories or fragments? Behavioral and Brain Sciences 40 (e253), pp. 30-31. ISSN 0140-525X.
|
Text
21142.pdf - Author's Accepted Manuscript Download (485kB) | Preview |
Abstract
Lake et al. argue persuasively that modelling human-like intelligence requires flexible, compositional representations in order to embody world knowledge. But human knowledge is too sparse and selfcontradictory to be embedded in “intuitive theories.” We argue, instead, that knowledge is grounded in exemplar-based learning and generalization, combined with high flexible generalization, a viewpoint compatible both with non-parametric Bayesian modelling and with subsymbolic methods such as neural networks.
Metadata
| Item Type: | Article |
|---|---|
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Psychological Sciences |
| Depositing User: | Administrator |
| Date Deposited: | 09 Feb 2018 12:52 |
| Last Modified: | 02 Aug 2023 17:39 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/21142 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
