Cooper, Richard P. (2017) Deep-learning networks and the functional architecture of executive control. Behavioral and Brain Sciences 40 , e261. ISSN 0140-525X.
|
Text
18017.pdf - Author's Accepted Manuscript Download (364kB) | Preview |
Official URL: https://doi.org/10.1017/S0140525X17000103
Abstract
Lake et al. underrate both the promise and the limitations of contemporary deep learning techniques. The promise lies in combining those techniques with broad multisensory training as experienced by infants and children. The limitations lie in the need for such systems to possess functional subsystems that generate, monitor and switch goals and strategies in the absence of human intervention.
Metadata
| Item Type: | Article |
|---|---|
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Psychological Sciences |
| Research Centres and Institutes: | Cognition, Computation and Modelling, Centre for |
| Depositing User: | Rick Cooper |
| Date Deposited: | 01 Feb 2017 18:03 |
| Last Modified: | 02 Aug 2023 17:31 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/18017 |
Statistics
Downloads
Activity Overview
6 month trend
6 month trend
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
Edit/View Item