Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework
Fig 5
Constraining the connectivity.
Connectivity after training for the context-dependent integration task (Fig 4), when the connection matrix is (A) unstructured and (B) structured. Both networks consist of 150 units (120 excitatory, 30 inhibitory). In B the units are divided into two equal-sized “areas,” each with a local population of inhibitory units (IS and IM) that only project to units in the same area. The “sensory” area (green) receives excitatory inputs and sends dense, “long-range” excitatory feedforward connections EM ← ES to the “motor” area (orange) from which the outputs are read out. The sensory area receives sparse excitatory feedback projections ES ← EM from the motor area.