In this paper, we propose and analyze a three-step general iteration method which is special case of an proposed in (S. Thianwan S. Suantai, Convergence criteria new with errors for nonexpansive nonself-mappings, Comput. Math. Appl. 52 (2006), 1107-1118). Here intend to study directly the accumulation, estimation control random newly method. We give conditions under accumulated-error our bounde...

In the main paper, we have reviewed variants of AIPs according to the loss functions and the optimisation algorithms. Algorithms FGV, FGS, BI, and GA use the softmax-log loss − log f̂ . The DeepFool (DF) and our GAMAN variants use the difference of two scores (e.g. f ? − f). This section includes an auxiliary analysis for the effect of the loss type: softmax-log loss− log f̂ versus score loss −f ...