full-FORCE: A Target-Based Method for Training Recurrent Networks
This method improves training efficiency and robustness for modeling dynamic neural computations, though it appears incremental as it builds on existing FORCE techniques.
The authors tackled the problem of training recurrent networks for complex temporal tasks by introducing a target-based method that modifies the full connectivity matrix, resulting in networks with fewer neurons and greater noise robustness compared to traditional approaches.
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.