Deep-learning networks and the functional architecture of executive control
- PMID: 29342687
- DOI: 10.1017/S0140525X17000103
Deep-learning networks and the functional architecture of executive control
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.
Comment in
-
Ingredients of intelligence: From classic debates to an engineering roadmap.Behav Brain Sci. 2017 Jan;40:e281. doi: 10.1017/S0140525X17001224. Behav Brain Sci. 2017. PMID: 29342708
Comment on
-
Building machines that learn and think like people.Behav Brain Sci. 2017 Jan;40:e253. doi: 10.1017/S0140525X16001837. Epub 2016 Nov 24. Behav Brain Sci. 2017. PMID: 27881212
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
