我试图掌握神经网络背后的想法(完全),所以我开始创建自己的simple perceptron算法。
这是我的代码(在JavaScript中):
var lr = 0.1;//learning rate
//Initiate the weights randomly
function initWeights(weights, trainingSets){
for(var i=0; i<trainingSets[0].in.length; i++){
weights[i] = Math.random()*2 - 1;
}
weights.push(Math.random()*2 - 1); //b
}
//Return the raw activation value for a giving trainingSet
function getSum(weights, trainingSet){
var sum = 0;
for(var i=0; i < trainingSet.in.length; i++){
sum += weights[i]*trainingSet.in[i];
}
sum += 1 * weights[weights.length-1];
return sum;
}
//Activation function
function activate(value){
return (value >= 0)? 1 : 0;
}
function train(weights, trainingSets){
var error = 0;
for(var i=0; i<trainingSets.length; i++){
var currentSet = trainingSets[i];
var activationValue = getSum(weights, currentSet);
var error = currentSet.out - activate(activationValue);
error += error;
for(var j=0; j<weights.length-1; j++){
var deltaW = error * lr * currentSet.in[j];
weights[j] += deltaW;
}
weights[weights.length-1] += error * lr * 1;
}
return error/(weights.length);
}
var inp = [
{in:[1,1], out:1},
{in:[0,0], out:0},
{in:[0,1], out:0},
];
var w = [];
initWeights(w, inp);
//for(var j = 0; j < inp.length; j++){
var error = 1;
while(error >= 0.01){
error = train(w, inp);
}
//}
console.log("===")
var tester = {in:[1,0], out: NaN};
console.log(getSum(w, tester)) //should be negative
console.log("y=("+w[1]+"*x+"+w[2]+")/"+w[1])
结果不一致,(我使用AND算法来学习)
情节应该如下:
但通常看起来像这样:
我确信我在这里错过了一些小事 提前谢谢。
答案 0 :(得分:1)
您的代码至少有三个问题:
0
的一个训练示例归为{ {1}},它会导致代码中出现否定错误,因此培训会停止,即使它远未结束用
训练后,这是不正确的1
你会得到var inp = [
{in:[1,1], out:1},
{in:[0,0], out:0},
{in:[0,1], out:0},
];
,这不是感知器的工作方式。它只会在2维平面上找到这样一条线,f( [1,0] ) == 0
位于其一侧,[1,1]
和[0,0]
位于另一侧。无法保证[0,1]
与[1,0]
和[0,0]
位于同一侧,这是预期行为。使用提供的数据,感知器没有理由不使用[0,1]
的垂直线,这可以完美地分隔您的数据,但x=0.5
。您的训练数据不会“定义”和操作,只是一组简单的规则,无数分类器都会遵守这些规则。
f( [1,0] ) == 1
如评论中所述,如果您使用点(1,0),(0,1)和(1,1)的值训练您的网络,它将自己推断(0,0)的值
function train(weights, trainingSets){
var error = 0;
for(var i=0; i<trainingSets.length; i++){
var currentSet = trainingSets[i];
var activationValue = getSum(weights, currentSet);
var error_current = currentSet.out - activate(activationValue);
error += Math.abs( error_current );
for(var j=0; j<weights.length-1; j++){
var deltaW = error_current * lr * currentSet.in[j];
weights[j] += deltaW;
}
weights[weights.length-1] += error_current * lr * 1;
}
return error/(weights.length);
}
产生
var inp = [
{in:[1,1], out:1},
{in:[0,1], out:0},
{in:[1,0], out:0},
];
var w = [];
initWeights(w, inp);
//for(var j = 0; j < inp.length; j++){
var error = 1;
while(error >= 0.01){
error = train(w, inp);
}
//}
console.log("===")
var test = [
{in:[1,1], out:1},
{in:[0,0], out:0},
{in:[0,1], out:0},
{in:[1,0], out:0},
];
for(var i=0; i<test.length; ++i){
console.log(test[i].in + " out: " +test[i].out + " nn: " + activate(getSum(w, test[i]) ) );
}