【问题标题】:Need help on Hopfield Simulation function需要有关 Hopfield 模拟功能的帮助
【发布时间】:2023-03-03 01:25:02
【问题描述】:

我已经使用 newhop 函数训练了一个 Hopfiled 网络,当我为我的测试输入数据模拟这个网络时,[y,Pf,Af] = sim(net,{1 repeatnum},{},{im1}); 它工作正常,但问题是它获取迭代次数作为输入参数,例如100 次迭代。网络可能会在输入数据上收敛,例如在第 5 次迭代中,无需继续模拟。有什么方法可以模拟直到网络收敛?

问候!

【问题讨论】:

    标签: matlab neural-network


    【解决方案1】:

    查看net.adaptParam.goal。

    如有必要,请根据help nntrain的帮助,正确设置net.adaptFcn和net.adaptParam。

    来自help traingd:

    Training stops when any of these conditions occurs:
     1) The maximum number of EPOCHS (repetitions) is reached.
     2) The maximum amount of TIME has been exceeded.
     3) Performance has been minimized to the GOAL.
     4) The performance gradient falls below MINGRAD.
     5) Validation performance has increased more than MAX_FAIL times
        since the last time it decreased (when using validation).
    

    【讨论】:

      猜你喜欢
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      相关资源
      最近更新 更多