A Poster

Here's a picture of the poster.

Began to design the poster

We began to design the poster. This poster aims to attract more people’s attention on the result of our project. We wanted that the poster could stand out from others while it was academic enough. This is a master plate that we will imitate.

Use network to forecast

[input_con, target_con] = concrete_dataset();

% new_target = [];

%    new_input = [];

%    dimension=size(input);

   t=target_con.';

   p=input_con.';

 net = fitnet(50);

    net = train(net,p,t);

 %   view(net)

    y = net(p);

    plotregression(t,y);

The effect of the learning rate.

P = [0.5152 0.8173 1.0000;
     0.8173 1.0000 0.7308;
     1.0000 0.7308 0.1390;
     0.7308 0.1390 0.1087;
     0.1390 0.1087 0.3520;
     0.1087 0.3520 0.0000;]';
T=[0.7308 0.1390 0.1087 0.3520 0.0000 0.3761];
net=newff([0 1;0 1;0 1],[5,1],{'tansig','logsig'},'traingd');
net.trainParam.epochs=1000;
net.trainParam.goal=0.01;
LP.lr=0.01;
net=train(net,P,T);

If the learning rate is too large, it may swing between inappropriate solution.
If the learning rate is too small, the learning will be very slow.

learning rate=0.01:the performance=0.128
learning rate=0.1:the performance=0.185
learning rate=0.2:the performance=0.337
learning rate=0.5:the performance=0.308