Python人工智能大师课（一）

《Python人工智能大师课》是一门面向零基础学习者的系统化AI实战课程，涵盖机器学习、深度学习和强化学习核心领域。课程从数学基础与Python编程入门开始，无需学员具备先验知识，通过可视化任务和代码实践循序渐进地讲解算法原理与实现。内容包含监督/无监督学习、模型优化、CNN/RNN/Transformer等深度学习架构、Q学习/PPO/A3C等强化学习算法，以及贝叶斯模型、神经架构搜索等高级主题。课程强调理论结合实践，采用Python、PyTorch、Julia和Colab等多种工具，适合希望扎实掌握人工智能技术本质的学习者。

MP4 | 视频：h264，1920×1080 | 音频：AAC，44.1 KHz，2 Ch 语言：英语 | 时长：18小时37分钟


Artificial Intelligence Masterclass with Python 。Learn AI from scratch with hands-on projects: Machine Learning, Deep Learning, Reinforcement Learning。This course is built for learners who want a serious, structured path into Artificial Intelligence. Whether you’re coming from engineering, programming, or analytics — or even starting from scratch — you’ll find that everything here is laid out in a practical, step-by-step format.We start with foundational math and basic Python — so you don’t have to worry if you haven’t used linear algebra or probability in a while. You’ll get clear walkthroughs of the math behind algorithms, with Python implementations that you can run, change, and learn from directly.From there, we cover all the major building blocks of modern AI:Supervised and unsupervised learningModel accuracy and regularizationDeep learning with CNNs, RNNs, and TransformersReinforcement learning methods like Q-Learning, PPO, A3C, TRPOBayesian models, optimization methods, and neural architecture searchYou’ll work with real code, solve tasks visually, and understand why each method works — not just how to use it. We also use a mix of Python, PyTorch, Julia, and Colab notebooks where appropriate.If you’re looking for an over-the-top promo, you won’t find it here. This course is detailed, technical, and designed to make sure you walk away actually understanding AI.All content is developed and presented by Advancedor Academy.

What you’ll learn
Understand the foundational math behind AI, including linear algebra, probability, and optimization.
Build and train machine learning models from scratch using Python and PyTorch.
Develop deep learning systems such as CNNs, RNNs, Transformers, and Autoencoders with real code.
Apply reinforcement learning algorithms including SARSA, Q-learning, PPO, and A3C in interactive environments.
Use techniques like PCA, regularization, and cross-validation to improve model performance.
Explore advanced topics such as Graph Neural Networks, Bayesian methods, and Meta-Learning with working examples.

Requirements
No prior background in AI is required.
Basic programming knowledge helps, but there’s an optional Python section at the beginning for anyone who needs it.
You’ll need a computer that can run Python and a stable internet connection to follow along with the tools and notebooks.

课程目录：
1 – 引言
2 – 向量与向量运算理论
3 – 向量与向量运算实践
4 – 概率论基础
5 – 机器学习导论
6 – 机器学习流程
7 – 机器学习Python库概览
8 – 机器学习核心概念 – 1
9 – 机器学习核心概念 – 2
10 – 机器学习核心概念 – 3
11 – 机器学习核心概念 – 4
12 – 符号表示法
13 – 什么是学习
14 – 为何要预测函数 f
15 – 维度灾难
16 – 如何预测函数 f
17 – 预测准确性与模型简洁性
18 – 回归 vs 分类
19 – 预测质量评估
20 – 偏差-方差权衡
21 – 分类问题设置
22 – KNN 示例
23 – 回归的数学基础
24 – 回归 – 视觉解释
25 – 多元线性回归
26 – 普通最小二乘法(OLS)表
27 – 假设检验
28 – KNN 介绍
29 – 引言 (此处可能指新章节的引言)
30 – 朴素贝叶斯项目
31 – 引言 (此处可能指新章节的引言)
32 – 项目 – 逻辑回归(LR)
33 – 混淆矩阵
34 – 准确率
35 – 精确率
36 – 召回率
37 – F1分数
38 – ROC-AUC曲线
39 – 对数损失(Log-Loss)
40 – 交叉验证
41 – K折交叉验证 – 回归
42 – K折交叉验证 – 分类
43 – 网格搜索与随机搜索
44 – 正则化的数学基础
45 – 支持向量机(SVM)的数学基础 – 1
46 – 支持向量机(SVM)的数学基础 – 2
47 – 核函数
48 – SVM 成本函数
49 – 基础 (此处可能指新章节的基础知识)
50 – 基尼指数与过拟合
51 – 随机森林 – 介绍
52 – 提升法(Boosting) – 第1部分
53 – 提升法(Boosting) – 第2部分
54 – 无监督学习导论
55 – K均值聚类 – 第1部分
56 – K均值聚类 – 第2部分
57 – 降维 – 主成分分析(PCA) – 1
58 – 降维 – PCA (鸢尾花数据集示例)
59 – PCA (MNIST数据集示例)
60 – 神经网络导论
61 – 深度学习架构 – 卷积神经网络(CNN)
62 – 使用PyTorch实现CNN架构
63 – 使用Julia (Flux)实现CNN架构
64 – 使用MATLAB实现CNN架构
65 – 1993年 Yann LeCun (可能指其开创性工作)
66 – 使用PyTorch实现MLP-Mixer结构
67 – 使用Python实现残差网络(ResNet) – 1
68 – 使用Python实现残差网络(ResNet) – 2
69 – 什么是Python
70 – Anaconda & Jupyter & Visual Studio Code
71 – Python语法与基本操作
72 – 数据结构 – 列表, 元组, 集合
73 – 控制结构与循环
74 – 函数与基础函数式编程
75 – 中级函数
76 – 字典与高级数据结构
77 – 模块、包与库导入
78 – 文件处理
79 – 异常处理与健壮代码
80 – 面向对象编程(OOP)
81 – 数据可视化基础
82 – 高级列表操作与推导式
83 – 数据质量
84 – 数据清洗技术
85 – 处理缺失值
86 – 处理异常值
87 – 特征缩放与归一化
88 – 标准化
89 – 分类变量编码
90 – 特征工程
91 – 降维