Research Article

Building Recurrent Neural Networks to Implement Multiple Attractor Dynamics Using the Gradient Descent Method

Figure 4

Time series generated by the trained RNN in experiment 1. For each time series, only the initial state is different.
846040.fig.004a
(a)
846040.fig.004b
(b)
846040.fig.004c
(c)
846040.fig.004d
(d)
846040.fig.004e
(e)