Fig. 4 Performance comparison in the Santa Fe time-series prediction (the same maximum network size).
In Fig. 4, the parameters of the four sparse algorithms are chosen such that the algorithms yield almost the same maximum network size, while in Fig. 5, the parameters of the sparse algorithms are chosen such that they produce almost the same MSE at the end of adaptation.
Furthermore, the IPA algorithm that generates networks will not continue if the network reaches the pre-specified maximum network size (i.e., 140 genes), which might rule out many nodes with small degrees of connectivity and impact the scale-free behavior.
If the gene network does not reach the maximum network size (140 genes in this study), IPA will then connect additional genes/networks from its database to any of the genes involved in the gene network.
IPA builds networks by querying the Ingenuity Pathways Knowledge Base for interactions between the identified genes and all other gene objects stored in the knowledge base; it then generates networks with a maximum network size of 35 genes/proteins.
Although individuals were allowed to indicate how many more individuals past 10 they could nominate, answers were either vague (e.g. "many more") or were subject to lumping around specific values ending in 0 or 5, therefore, the maximum network size used in the RDS analysis was set to 10.
