This paper expatiates the stability and bifurcation for a fractional-order neural network (FONN) with double leakage delays. Firstly, the characteristic equation of the developed FONN is circumspectly researched by employing inequable delays as bifurcation parameters. Simultaneously the bifurcation criteria are correspondingly extrapolated. Then, unequal delays-spurred-bifurcation diagrams are primarily delineated to confirm the precision and correctness for the values of bifurcation points. Furthermore, it lavishly illustrates from the evidence that the stability performance of the proposed FONN can be demolished with the presence of leakage delays in accordance with comparative studies. Eventually, two numerical examples are exploited to underpin the feasibility of the developed theory. The results derived in this paper have perfected the retrievable outcomes on bifurcations of FONNs embodying unique leakage delay, which can nicely serve a benchmark deliberation and provide a comparatively credible guidance for the influence of multiple leakage delays on bifurcations of FONNs.

本文阐述了具有双泄漏延迟的分数阶神经网络（FONN）的稳定性和分支。首先，以不等时延为分岔参数，对发达的FONN的特征方程进行了研究。同时，相应地推断出分叉标准。然后，主要画出不等时激励分叉图，以确认分叉点值的精度和正确性。此外，根据比较研究，它从证据中充分说明了所提出的FONN的稳定性能可以在存在泄漏延迟的情况下拆除。最终，利用两个数值示例来证明所开发理论的可行性。