Recurrent neural networks that learn multi-step visual routines with reinforcement learning
Fig 3
The network comprises one input layer, two hidden layers and one output layer. The input and hidden layers have four features each. In each layer, units belong to the feedforward or to the recurrent group. The activity of units in the recurrent group is gated by input of neurons in the feedforward group with the same RF so that they cannot participate in the spread of enhanced activity in case the corresponding feedforward unit is inactive.