fullFORCE: A TargetBased Method for Training Recurrent Networks
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 month, 2 weeks ago.

fullFORCE: A TargetBased Method for Training Recurrent Networks
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a targetbased 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 leastsquares (FORCE) approaches. In addition, we show how introducing additional input signals into the targetgenerating 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, taskperforming network.
fullFORCE: A TargetBased Method for Training Recurrent Networks
by Brian DePasquale, Christopher J. Cueva, Kanaka Rajan, G. Sean Escola, L. F. Abbott
https://arxiv.org/pdf/1710.03070v1.pdf
You must be logged in to reply to this topic.