Deep Learning Academy · 课时

基础 RNN 单元

在多个步骤之间传递隐藏状态

基础 RNN 单元 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 2 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 a Cell Does

An RNN cell is the tiny engine that runs at each time step. You feed it one input and the old memory, and it returns the new memory.

Two Inputs Per Step

Every step the cell takes two things: the current input x and the previous hidden state. It mixes them into a fresh hidden state.

The Core Formula

The vanilla cell computes a weighted sum of input and memory, then squashes it. That single line is the heart of the RNN.

h_t = tanh(W_x @ x_t + W_h @ h_prev + b)

Why tanh?

The tanh activation keeps the hidden state bounded between -1 and 1, so memory values stay stable instead of blowing up over many steps.

Two Weight Matrices

One matrix W_x reads the new input; another W_h reads the old memory. The cell learns both to decide what to keep and what to add.

The Initial Hidden State

Before step one there is no memory, so the hidden state starts as a vector of zeros and gets filled in as the sequence flows through.

h0 = torch.zeros(hidden_size)

Unrolling Through Time

Picture the cell copied once per step, with memory passed along the chain. This view is called unrolling the network through time.

Outputs From Memory

Need a prediction at a step? Pass that step's hidden state through a small output layer to get logits or a value.

y_t = W_y @ h_t + b_y

Use It in PyTorch

PyTorch gives you nn.RNN so you don't hand-code the loop. You set input and hidden sizes, then feed a batched sequence.

rnn = nn.RNN(input_size=10, hidden_size=20)

Outputs and Final State

Calling the layer returns two things: the outputs at every step and the final hidden state, handy for classifying the whole sequence.

out, h_n = rnn(x)

The Catch

Vanilla RNNs work, but their memory fades fast over long sequences. That weakness sets the stage for gated cells like the LSTM.

Quick Check

What two things does a vanilla RNN cell take as input each step?

Recap

The vanilla cell blends input and old memory with tanh to make a new hidden state, repeated step by step across the sequence. ✅

常见问题解答

「基础 RNN 单元」课时是免费的吗？

是的 — 「基础 RNN 单元」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。

「基础 RNN 单元」这节课中我会学到什么？

在多个步骤之间传递隐藏状态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 2 节课，共 4 节。

「基础 RNN 单元」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