To　solve　the　problem　of　gradient　descent　(GD)　method　which　has　low　accuracy　and　easily　falling　into　local　optimum,　the　radial　basis　function　(RBF)　based　on　immune　algorithm　system　(IAS-RBF)　is　proposed.　In　this　method,　each　antibody　is　a　RBF　neural　network　and　the　optimal　affinity　is　calculated　by　immune　algorithm　system　(IAS)　to　get　the　best　antibody,　then　the　optimal　parameter　of　RBF　neural　network　(i.e.,　the　RBF　centers,　the　widths,　and　the　output　weights)　are　obtained.　The　simulation　results　show　that　IAS-RBF　overcomes　the　problem　of　premature　convergence,　and　has　a　better　accuracy　than　other　RBF　neural　networks.　©　2017　Technical　Committee　on　Control　Theory,　CAA.