how to compute and plot mean square error for two vectors?

Question

DEEPAK Chekuri 2021-1-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/712813-how-to-compute-and-plot-mean-square-error-for-two-vectors

评论： DEEPAK Chekuri 2021-1-13

i have a dataset to classify, using perceptron learning rule . i've calculated the weight matrix but don't know how to plot MSE .

{𝑝1 = [ 1 1 ],𝑡1 = [ 0 0 ]}, {𝑝2 = [ 1 2 ],𝑡2 = [ 0 0 ]}, {𝑝3 = [ 2 −1 ],𝑡3 = [ 0 1 ]}, {𝑝4 = [ 2 0 ],𝑡4 = [ 0 1 ]}, {𝑝5 = [ −1 2 ],𝑡5 = [ 1 0 ]}, {𝑝6 = [ −2 1 ],𝑡6 = [ 1 0 ]}, {𝑝7 = [ −1 −1 ],𝑡7 = [ 1 1 ]}, {𝑝8 = [ −2 −2 ],𝑡8 = [ 1 1 ]}.

This the dataset and w=[-2 0;0 -2],bias =[-1 0]

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Gaurav Garg 2021-1-13

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/712813-how-to-compute-and-plot-mean-square-error-for-two-vectors#answer_596678

Hi Deepak,

You can plot MSE/Loss and accuracy for each iteration of your training/testing.

To do this, you can make a network with 'n' number of layers, train your network on it and store the loss returned per iteration in a list. Finally, you can plot this loss on y-axis and number of iterations on x-axis.

For any more information on monitoring metrics, you can look at the documentation here.