Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework | PLOS Computational Biology
Skip to main content
Advertisement

< Back to Article

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 EMES to the “motor” area (orange) from which the outputs are read out. The sensory area receives sparse excitatory feedback projections ESEM from the motor area.

Fig 5

doi: https://doi.org/10.1371/journal.pcbi.1004792.g005