📄 instructions.html
字号:
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"><html><head> <title></title></head> <body text="#000000" bgcolor="#ffffff" link="#0000ef" vlink="#51188e" alink="#ff0000"> <h3>Adaline, (Optimal) Perceptron and Backpropagation Instructions</h3> <ul> <li>To specify a training set:</li> </ul> <ul> <ol> <li>Select a category to learn, <b>1/red</b> or <b>0/blue</b>.</li> <li>Click in the plane to place some points.</li> <li>Then change the category and click to place points in the other category.<br> <br> </li> </ol> <li>To train the network:<br> <br> </li> <ol> <li>First select a learning rule by clicking in the pop-up menu (near thetop left of the applet).</li> <li>Adjust the number of iterations and learning rate parameter in thefields near the bottom of the applet.</li> <li>Click the <b>Init</b> button to initialize the network to a randomset of weights.</li> <li>Click the <b>Learn</b> button to train the network. Trainingwill run for the number of iterations (epochs) you specified; you can continue training by clicking again on Learn or clicking the Play button. Clickingthe <b>Play</b> button is like clicking the Learn button repeatedly witha time intervall which you can specify in "delay".</li> <li>After training, the color of the input plane indicates the output value for that point (0.0=blue, 1.0=red).</li> </ol> <li>To compare learning rules, use the same data set each time. When you change the learning rule, don't forget to click the <b>Init </b>button before training.</li> <li>Click the <b>Clear</b> button to erase the training set.</li> </ul> <hr width="100%"><a href="index.html">[Back to the Adaline, Perceptron andBackprop applet page</a> ] <br></body></html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -