matlab - 在 MATLAB 中创建简单神经网络时的困惑

Question

我试图通过 MATLAB 创建一个简单的神经网络(引用 https://becominghuman.ai/making-a-simple-neural-network-2ea1de81ec20 ，虽然作者用 JavaScript 编写了代码，但我想使用 MATLAB 做同样的事情)。我创建了自己的 MATLAB Live Script，但我真的很困惑，因为我创建的权重向量没有更新。我试图将 0.20 的学习率添加到权重(3)元素中，以使其达到 1(我正在尝试 6 次试验来训练网络)。我是使用 MATLAB 的新手，通常使用 Python 编写代码，因此，如果我所犯的错误/我缺少的东西得到友好解释或者哪一行代码是错误的，我将不胜感激。非常感谢!

这是我的代码:-

inputs = [0 1 0 0]'
weights = [0 0 0 0]'
desiredresult = 1
disp('Neural Net Result')
res_net = evaluateNeuralNetwork(inputs, weights)
disp('Error')
evaluateNeuralNetError(1, res_net);
learn(inputs, weights)
train(6, inputs, weights)



function result = evaluateNeuralNetwork(inputVector, weightVector)
    result = 0;

    for i = 1:numel(inputVector)
        result = result + (inputVector(i) * weightVector(i));
    end
end

function res = evaluateNeuralNetError(desired, actual)
    res = desired - actual
end

    function learn(inputs, weights)
    learningRate = 0.20

         weights(3) = weights(3) + learningRate
end

function neuralNetResult = train(trials, inputs, weights)
    for i = 1:trials
        neuralNetResult = evaluateNeuralNetwork(inputs,weights)
        learn(inputs, weights)
    end
end

编辑

这是根据 Marouen 接受的答案更新的(工作代码):-

inputs = [0 1 0 0]'
weights = [0 0 0 0]'
desiredresult = 1
disp('Neural Net Result')
res_net = evaluateNeuralNetwork(inputs, weights)
disp('Error')
evaluateNeuralNetError(1, res_net);
learn(inputs, weights)
train(6, inputs, weights)



function result = evaluateNeuralNetwork(inputVector, weightVector)
    result = 0;

    for i = 1:numel(inputVector)
        result = result + (inputVector(i) * weightVector(i));
    end
end

function res = evaluateNeuralNetError(desired, actual)
    res = desired - actual
end

    function weights = learn(inputs, weights)
    learningRate = 0.20

         weights(3) = weights(3) + learningRate
end

function neuralNetResult = train(trials, inputs, weights)
    for i = 1:trials
        disp('Neural Network Result')
        neuralNetResult = evaluateNeuralNetwork(inputs,weights)
        weights = learn(inputs, weights)
        disp('Error')
        evaluateNeuralNetError(1, neuralNetResult)
    end
end

Answer 1

听起来您错过了 learn 函数中的循环，请仔细检查原始文章。

function learn(inputs, weights)
    learningRate = 0.20

    for i =1:length(weights)
        if(inputs(i)> 0)
            weights(i) = weights(i) + learningRate
        end
    end
end

编辑

您还必须在train函数的循环中更新权重

weights=learn(inputs, weights)

并在学习函数声明中添加权重作为输出

function weights=learn(inputs, weights)

否则权重不会更新。您还可以将 weights 声明为全局变量。