Figure 3. Interval-matching task.

(a) In the task, the RNN input consists of two input pulses, with a random delay $T_{\mathrm{delay}}$ between pulses in each trial. The target output (dashed line) is a pulse trailing the second input pulse by $T_{\mathrm{delay}}$. (b) The time of the peak in the RNN output is observed after training with RFLO learning and testing in trials with various interpulse delays in the input. Red (blue) shows the case in which the RNN is trained with interpulse delays satisfying $T_{\mathrm{delay}}\le 15\tau$ ($20\tau$). (c) Same as (b), but with the RNN trained using BPTT using interpulse delays $T_{\mathrm{delay}}\le 25\tau$ for training and testing.