full-FORCE: A target-based method for training recurrent networks

Brian DePasquale, Christopher J Cueva, Kanaka Rajan, G Sean Escola and L F Abbott

PLOS ONE, 2018, vol. 13, issue 2, 1-18

Abstract: Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during training to provide suitable “target” dynamics useful for performing the task. Because it exploits the full recurrent connectivity, the method produces networks that perform tasks with fewer neurons and greater noise robustness than traditional least-squares (FORCE) approaches. In addition, we show how introducing additional input signals into the target-generating network, which act as task hints, greatly extends the range of tasks that can be learned and provides control over the complexity and nature of the dynamics of the trained, task-performing network.

Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0191527 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 91527&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0191527

DOI: 10.1371/journal.pone.0191527

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().