Deep Learning Academy · 课时

LeNet 与 AlexNet：最初的成功

了解现代 CNN 的起点

第 1 / 4 课13 个步骤

LeNet 与 AlexNet：最初的成功 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 1 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。

Where CNNs Began

Long before todays giants, two small networks proved that learned convolutions could read images. Lets meet the pioneers.

LeNet-5 Reads Digits

In 1998 Yann LeCun built LeNet-5 to recognize handwritten digits on checks. It was tiny, but it worked beautifully.

A Simple Recipe

LeNets pattern was clear: alternate convolution and pooling layers, then finish with a few dense layers. That recipe still echoes today.

Trained End to End

The big idea was that LeNet learned its filters from data by backpropagation, instead of an engineer hand-coding edge detectors.

Then Came the Pause

Data and compute were scarce, so progress stalled for years. The world was not yet ready to scale this idea up.

AlexNet Wakes the Field

In 2012 AlexNet crushed the ImageNet contest, halving the error rate and igniting the modern deep learning boom.

Bigger and Deeper

AlexNet was a scaled-up LeNet: more layers, far more filters, and millions of parameters hungry for data.

ReLU Speeds Training

AlexNet swapped slow saturating activations for the fast, simple ReLU, letting a deep net train in a reasonable time.

Trained on Two GPUs

It ran on two GPUs in parallel. That hardware choice turned an old idea into a practical, winning system.

Dropout Fights Overfit

To stop memorizing, AlexNet added dropout in its dense layers, randomly silencing neurons during training.

import torch.nn as nn
classifier = nn.Sequential(nn.Dropout(0.5), nn.Linear(4096, 1000))

A Conv Layer in PyTorch

Both nets are stacks of one core block. Here is a single Conv2d layer, the brick everything is built from.

import torch.nn as nn
layer = nn.Conv2d(in_channels=3, out_channels=96, kernel_size=11, stride=4)

Quick Check

Think about what made AlexNet so influential.

在交互式课程中回答

Recap: The First Wins

LeNet showed CNNs could learn, and AlexNet proved they could win at scale. Together they launched the era you are studying. Nice start!

免费开始

用 AI 导师学习 Python — 免费

在浏览器中编写并运行真实代码，获得全天候 AI 导师的即时帮助，并在网页或应用中继续学习。

课程: 30
课程: 120

免费开始学习查看完整课程

常见问题解答

「LeNet 与 AlexNet：最初的成功」课时是免费的吗？

是的 — 「LeNet 与 AlexNet：最初的成功」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。

「LeNet 与 AlexNet：最初的成功」这节课中我会学到什么？

了解现代 CNN 的起点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 1 节课，共 4 节。

「LeNet 与 AlexNet：最初的成功」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