Deep Learning Academy · 课时

ReLU 及其 Leaky 和 GELU 变体

了解默认激活函数与现代变体

ReLU 及其 Leaky 和 GELU 变体 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。

Meet ReLU

The most popular activation is ReLU: it keeps positive values and turns every negative one into zero. Simple and fast. ⚡

import torch.nn.functional as F
y = F.relu(x)   # max(0, x), elementwise

Why It Caught On

ReLU is cheap to compute and its gradient is a clean 1 for positives. That keeps signals flowing and makes deep nets train quickly.

The Math

ReLU is just max(0, x). Positive inputs pass straight through; negatives flatten to zero. That single hinge is the whole trick.

The Dying ReLU Problem

If a neuron always outputs zero, its gradient is zero too, so it stops learning forever. We call this a dead neuron. 💀

Leaky ReLU to the Rescue

Leaky ReLU lets a tiny slope through for negatives instead of a hard zero. That small leak keeps dead neurons alive.

y = F.leaky_relu(x, negative_slope=0.01)

Parametric ReLU

PReLU goes further: it learns the negative slope during training instead of fixing it. The network tunes the leak itself.

Meet GELU

GELU smooths the ReLU corner into a soft curve. It gates inputs by how likely they are to be useful, not with a hard cutoff.

y = F.gelu(x)

Why Transformers Love GELU

Modern models like transformers favor GELU because its smooth shape gives gentler gradients. That often means steadier training. 🤖

SiLU and Friends

SiLU, also called Swish, multiplies the input by its own sigmoid. Like GELU, it is smooth and frequently edges out plain ReLU.

A Sensible Default

Start with ReLU for hidden layers; it is fast and reliable. Reach for Leaky ReLU or GELU only if you see dead neurons or want extra smoothness.

Use It as a Layer

You can drop these in as modules inside a model, not just as functions. That makes them easy to chain in nn.Sequential.

import torch.nn as nn
net = nn.Sequential(nn.Linear(4, 8), nn.ReLU())

Quick Check

Think about a neuron that always lands in the negative zone.

Recap

ReLU is the fast default, but it can let neurons die. Leaky ReLU, PReLU, and GELU smooth or leak the negatives to keep learning healthy. 🌟

常见问题解答

「ReLU 及其 Leaky 和 GELU 变体」课时是免费的吗？

是的 — 「ReLU 及其 Leaky 和 GELU 变体」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。

「ReLU 及其 Leaky 和 GELU 变体」这节课中我会学到什么？

了解默认激活函数与现代变体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。

「ReLU 及其 Leaky 和 GELU 变体」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