May 2025
Beginner to intermediate
252 pages
3h 16m
Chinese
Content preview from 从零开始学习深度学习Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
索引
符号
- 一维卷积，计算一维卷积的梯度-一维卷积与批处理：后向传递
- 二维卷积，二维卷积-二维卷积：编码后向传递
A
- 累积梯度、编码向上梯度累积、为 RNN 中的权值累积梯度
- 激活功能,与大脑的联系,激活功能说明--一个快乐的媒介：Tanh
- autoencoders，一种处理无标签情况的方法--在 PyTorch 中 实现自动编码器
- 自动分化（autodiff），自动分化--解释发生了什么
- 平均池化，池化层
B
C
- 连锁规则
- 字符级 RNN，基于字符级 RNN 的语言模型的数据表示--将这一切结合起来
- 代码示例, 获取和使用,使用代码示例
- 评论和问题,如何联系我们
- 计算图
- 卷积滤波器，多通道卷积操作
- 卷积 层，卷积层--将CNN 应用于图像之外
- 卷积神经网络（CNNs）
- 卷积 层，卷积层--将CNN 应用于图像之外
- 矩阵乘法，通过矩阵乘法进行卷积-通过矩阵乘法进行 卷积
- 多通道操作，实现多通道卷积操作--反向传递
- 卷积神经网络概述
- PyTorch 中的 卷积神经网络--PyTorch中的 LSTMs
- 表征学习、神经网络和表征学习--多通道卷积操作
- 训练 CNN，使用此操作训练 CNN--实验
- 卷积, 卷积运算
D
- 数据
- 图像数据、神经网络和表征学习
- MNIST 数据集、实验、数据加载器和变换
- 预处理,数据预处理
- 无标签数据，一种处理无标签情况的方法
- 深度卷积神经网络,卷积层
- Deep Learning
- 建筑模型，积木上的积木--密集层
- 完整的培训代码，将所有内容整合在一起
- 层和类的交互，从零开始的 Deep Learning-NeuralNetwork：代码
- 神经网络的构件》中的层：层--与大脑的 连接
- NeuralNetwork类、The NeuralNetwork 类和 Maybe Others-Loss类
- 操作类，神经网络的构件：操作-代码
- 概述、Deep Learning 定义：初探
- 训练器和优化器类、训练器和优化器-训练器代码
- 训练目标，关于神经网络的一些直觉
- 致密层，致密层
- 衍生产品
- 代码描述，代码
- 定义、衍生产品
- 图表表示, 图表
- 有多个输入的函数 的导数, 有多个输入的函数的导数
- 多矢量输入函数的 导数，多矢量输入函数的导数--代码
- 数学描述,数学
- 点状产品，从现有功能创建新功能
- 下采样、汇集图层
- 辍学者
E
- 提前停止，列车代码
- 纪元，培训师
- 爆炸梯度问题，"Vanilla "RNN 节点的局限性
- 扩展
- 辍学，辍学实验：辍学
- 关于神经网络的直觉，关于神经网络的一些直觉--关于神经网络的 一些直觉
- 学习率衰减，学习率衰减-实验：学习率衰减
- MNIST 数据集实验，实验-实验：Softmax 交叉熵损失
- 动量，动量实验：随机梯度下降与动量
- 概述，扩展
- in PyTorch,在 PyTorch 中优化学习的技巧
- Softmax Cross Entropy Loss, Softmax Cross Entropy Loss Function-Ahappy medium：Tanh
- 权重初始化，权重初始化-实验：权重初始化 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.