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

8Citations
Citations of this article
85Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

DePasquale, B., Cueva, C. J., Rajan, K., Escola, G. S., & Abbott, L. F. (2018). full-FORCE: A target-based method for training recurrent networks. PLoS ONE, 13(2). https://doi.org/10.1371/journal.pone.0191527

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free