HI EVERY ONE how can i develop a general equation for the training neural net work results as shown below and how can i make these equations linear or non linear

Question

muqdad aljuboori 2015-8-20

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/234769-hi-every-one-how-can-i-develop-a-general-equation-for-the-training-neural-net-work-results-as-sh

回答： Greg Heath 2015-8-28

% ===== NEURAL NETWORK CONSTANTS =====
% Input 1
x1_step1_xoffset = [0.335;0.335;0.501;0.102];
x1_step1_gain = [3.01659125188537;3.01659125188537;4.01606425702811;2.23214285714286];
x1_step1_ymin = -1;
% Layer 1
b1 = [0.70223325258608282;0.24104166905986787;0.15348156236755661;0.71745208472067135;1.0923437909596025;-0.95136708708664663;-0.2046868130938489;0.69549692559132981;0.70255125958906395;0.53378139024323834];
IW1_1 = [0.31553367340711991 -0.40137059105569073 -0.22075607834007485 0.5348647692271854;-0.092030091983253126 -0.28374584174349826 0.20649380927946556 0.35735939709861786;0.32776169040220832 0.050294626086545419 0.079667428618699215 0.50081651896574708;-0.14811804808977719 0.38151873789393176 0.017981906558287995 0.66424811151304852;-0.37652540039941323 0.97877832998161851 -0.077044057346401851 -0.51900261587883245;-0.32720151455381563 0.42742966055003245 -0.35517724643687826 0.50098153225098097;-0.051448362732210991 0.0082648279513306416 -0.86709811026715733 -0.39857638994588535;0.46109450080528508 -0.066531109937333383 -0.041113866300515452 -0.56353092984647901;0.80083018038171372 -0.88583750768332392 -0.063517585064946633 0.81425789700412732;0.079986908269888413 -0.22913002954215689 -0.31306995793356845 -0.38078052790236266];
% Layer 2
b2 = [0.091922137693532732;-0.019433047791502147;0.69939781374412402];
LW2_1 = [0.55261567997791849 0.1160223164052863 -0.047616424378837022 0.42605645022894073 -0.10415185746376703 0.06618768395919053 0.0010938058921189939 -0.6341905607646755 -0.012011661547148993 -0.69437567292807567;0.17306699275597687 0.89820835369168806 0.58079560414251308 0.18560768732162328 0.31513562885346247 0.67277236054086276 0.36880119902800917 0.18586934718597467 -0.083078511715570055 -0.86733076931692943;-0.95085049127019827 0.06753786869036002 -0.42801674583698929 0.94677747671052259 -0.91050254600951541 0.049169317644063827 0.30599676599180614 -0.53164266498283019 0.78422577249919112 -0.54830037775898877];
% Output 1
y1_step1_ymin = -1;
y1_step1_gain = [2.17155266015201;2.1978021978022;4.96277915632754];
y1_step1_xoffset = [0.075;0.075;0.034];
% ===== SIMULATION ========
% Dimensions
Q = size(x1,2); % samples
% Input 1
xp1 = mapminmax_apply(x1,x1_step1_gain,x1_step1_xoffset,x1_step1_ymin);
% Layer 1
a1 = tansig_apply(repmat(b1,1,Q) + IW1_1*xp1);
% Layer 2
a2 = repmat(b2,1,Q) + LW2_1*a1;
% Output 1
y1 = mapminmax_reverse(a2,y1_step1_gain,y1_step1_xoffset,y1_step1_ymin);
end

% ===== MODULE FUNCTIONS ========

% Map Minimum and Maximum Input Processing Function function y = mapminmax_apply(x,settings_gain,settings_xoffset,settings_ymin) y = bsxfun(@minus,x,settings_xoffset); y = bsxfun(@times,y,settings_gain); y = bsxfun(@plus,y,settings_ymin); end

% Sigmoid Symmetric Transfer Function function a = tansig_apply(n) a = 2 ./ (1 + exp(-2*n)) - 1; end

% Map Minimum and Maximum Output Reverse-Processing Function function x = mapminmax_reverse(y,settings_gain,settings_xoffset,settings_ymin) x = bsxfun(@minus,y,settings_ymin); x = bsxfun(@rdivide,x,settings_gain); x = bsxfun(@plus,x,settings_xoffset); end