Figure 3.

Comparing the effects of structure learning and delay learning. Learning the structure does not make a huge difference with lower sparsity, but as it increases the benefit becomes clear. This might not be that surprising, since these methods were built to train highly sparse models. Delay learning improves the results with a fixed connectivity matrix, as was also shown in (Hammouamri et al., 2023). The benefits of delay learning are not obvious when the structure is learnt.