Deep Learning Academy · 课时

从零开始编写感知器

用几行 Python 代码实现一个神经元

从零开始编写感知器 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 3 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 Deep Learning Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Deep Learning Academy 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

What Is a Perceptron

A perceptron is one neuron plus a learning rule. It is the original trainable building block of neural networks, and you can code it from scratch. 🛠️

Start with Weights

First create the weights and a bias. Starting them at zero is fine for a perceptron; learning will move them where they need to be.

weights = [0.0, 0.0]
bias = 0.0

Predict with a Step

The predict step computes the weighted sum, then applies the step function to return 0 or 1.

score = w[0]*x[0] + w[1]*x[1] + bias
return 1 if score >= 0 else 0

Measure the Error

Compare the prediction to the true label. The error is simply target minus prediction: 0 when right, plus or minus one when wrong.

error = target - prediction

The Update Rule

The update rule nudges each weight by the error times the input. Wrong guesses push the weights toward the correct answer.

w[i] += lr * error * x[i]

Update the Bias Too

The bias learns the same way, but its input is always 1. So you simply add the learning rate times the error.

bias += lr * error

The Learning Rate

The learning rate scales how big each update is. Small values learn slowly but steadily; large ones can overshoot the answer.

lr = 0.1

One Pass: an Epoch

Looping once over every training example is called an epoch. You usually repeat for several epochs until mistakes stop.

The Training Loop

Each step of training predicts, measures error, and updates the weights and bias. Repeat across the dataset to learn.

for x, target in data:
    err = target - predict(x)
    update(x, err)

It Learns AND

Feed it the AND truth table and the perceptron converges fast. Both inputs must be 1 for it to output 1.

Convergence Guarantee

If the data is linearly separable, the perceptron is guaranteed to find a separating line. That promise is the convergence theorem.

Quick Check

Recall how a perceptron corrects itself.

Recap

A perceptron predicts with a step, measures error, and updates weights by lr times error times input. Repeat over epochs and it learns separable data. ✅

常见问题解答

「从零开始编写感知器」课时是免费的吗？

是的 — 「从零开始编写感知器」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Deep Learning Academy 课程的其余内容，请升级到 CoddyKit PRO。 Deep Learning Academy 课程共包含 4 节课。

「从零开始编写感知器」这节课中我会学到什么？

用几行 Python 代码实现一个神经元你通过在浏览器中直接运行的动手代码来练习 Deep Learning Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 Deep Learning Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 Deep Learning Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 3 节课，共 4 节。

「从零开始编写感知器」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 Deep Learning Academy 课中编写并运行代码吗？

能。每节 Deep Learning Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 Deep Learning Academy