# 深度学习(DL/ML)学习路径
最近几年,尤其是自从2016年Alpha Go打败李世石事件后,人工智能技术受到了各行业极大关注。其中以机器学习技术中深度学习最受瞩目。主要原因是这些技术在科研领域和工业界的应用效果非常好,大幅提升了算法效率、降低了成本。因而市场对相关技术有了如此大的需求。
我在思考传统行业与这些新兴技术结合并转型的过程中,亦系统的回顾了深度学习及其相关技术。本文正是我在学习过程中所作的总结。我将按照我所理解的学习路径来呈现各部分内容,希望对你亦有帮助。欢迎一起交流。
主要分为如下几个部分:
* **数学基础**:包括微积分、线性代数、概率论等对理解机器学习算法有帮助的基本数学。
* **Python**:`Python`提供了非常丰富的工具包,非常适合学习者实现算法,也可以作为工业环境完成项目。主流的深度学习框架,例如当前最流行的两个AI框架`TensorFlow`、`PyTorch`都以Python作为首选语言。此外,主流的在线课程(比如Andrew Ng在Coursera的深度学习系列课程)用Python作为练习项目的语言。在这部分,我将介绍包括Python语言基础和机器学习常用的几个Library,包括`Numpy`、`Pandas`、`matplotlib`、`Scikit-Learn`等。
* **机器学习**:介绍主流的机器学习算法,比如线性回归、逻辑回归、神经网络、SVM、PCA、聚类算法等等。
* **深度学习**:介绍原理和常见的模型(比如`CNN`、`RNN`、`LSTM`、`GAN`等)和深度学习的框架(`TensorFlow`、`Keras`、`PyTorch`)。
* **强化学习**:介绍强化学习的简单原理和实例。
* **实践项目**:这里将结合几个实际的项目来做比较完整的讲解。此外结合`Kaggle`、`阿里云天池`比赛来做讲解。
* **阅读论文**:如果你追求更高和更深入的研究时,看深度学习各细分领域的论文是非常必要的。
> 内容持续更新中,未完成的部分标识有TBD (To be done)。
> 文中涉及的公式部分是用[CodeCogs](https://codecogs.com/latex/eqneditor.php)的在线LaTeX渲染,如果公式未正确加载,可以尝试多刷新几次。
## 绪论
[机器学习绪论](machine-learning/machine-learning-intro.md)一文中总结了机器学习领域和其解决的问题介绍,建议先读此文,以便有一个系统认知。
## 数学基础
微积分和线性代数的基础是必须要掌握的,不然对于理解学习算法的原理会有困难。如果已经有一定的数学基础,可以先跳过这一部分,需要的时候再回来补。这里的Notes是基于Coursera中Mathematics for Machine Learning专题做的总结。
* [Calculus 微积分](math/calculus.md)
* [Linear Algebra 线性代数](math/linear-algebra.md)
* 概率论 (TBD)
* [PCA 主成分分析](math/pca.md)
## Python
如果有比较好的Python和机器学习相关Library的知识,对于学习算法过程中的代码可以快速理解和调试,一方面节省时间,另一方面也可以更聚焦在算法和模型本身上。
* [Python](python/python-basic)
* [Pandas](python/pandas)
* [NumPy](python/numpy)
* [Matplotlib](python/Matplotlib)
* [Scikit-Learn](python/Sklearn)
## 机器学习算法
主要基于Machine Learning (Coursera, Andrew Ng) 的课程内容。
* [机器学习算法系列](machine-learning/README.md)
* 内容参考包括:吴恩达Coursera系列、周志华《机器学习》、密西根大学Applied Machine Learning in Python
* 每章节配套的[<img src="img/github32.png" width="18" target="_blank" />Jupyter Notebook练习](https://github.com/loveunk/ml-ipynb) 参考网络内容修订
* 目录结构:
1. [绪论](machine-learning/machine-learning-intro.md)
1. [线性回归](machine-learning/linear-regression.md)
1. [逻辑回归](machine-learning/logistic-regression.md)
1. [神经网络](machine-learning/neural-networks.md)
1. [打造实用的机器学习系统](machine-learning/advice-for-appying-and-system-design.md)
1. [支持向量机 SVM](machine-learning/svm.md)
1. [聚类算法](machine-learning/clustering.md)
1. [数据降维](machine-learning/dimension-reduction.md)
1. [异常检测](machine-learning/anomaly-detection.md)
1. [推荐系统](machine-learning/recommender-system.md)
1. [大规模机器学习](machine-learning/large-scale-machine-learning.md)
1. [应用案例照片文字识别](machine-learning/photo-ocr.md)
1. [总结](machine-learning/ssummary.md)
## 深度学习
### Deep Learning 专题课程
主要基于Deep Learning (Coursera, Andrew Ng) 的专题课程 ,介绍深度学习的各种模型的原理。
* [深度学习](deep-learning/README.md)
1. 深度学习基础
- [深度学习基础](deep-learning/1.deep-learning-basic.md)
2. 深度神经网络调参和优化
- [深度学习的实践层面](deep-learning/2.improving-deep-neural-networks-1.practical-aspects.md)
- [深度学习优化算法](deep-learning/2.improving-deep-neural-networks-2.optimization-algorithms.md)
- [超参数调试、批量正则化和程序框架](deep-learning/2.improving-deep-neural-networks-3.pyperparameter-tuning.md)
3. 深度学习的工程实践
- [机器学习策略(1)](deep-learning/3.structuring-machine-learning-1.ml-strategy.md)
- [机器学习策略(2)](deep-learning/3.structuring-machine-learning-2.ml-strategy.md)
4. 卷积神经网络(CNN)
- [卷积神经网络](deep-learning/4.convolutional-neural-network-1.foundations-of-cnn.md)
- [深度卷积网络:实例探究](deep-learning/4.convolutional-neural-network-2.deep-convolutional-models.md)
- [目标检测](deep-learning/4.convolutional-neural-network-3.object-detection.md)
- [特殊应用:人脸识别和神经风格转换](deep-learning/4.convolutional-neural-network-4.face-recognition-and-neural-style-transfer.md)
5. 序列模型(RNN、LSTM)
- [循环序列模型(RNN)](deep-learning/5.sequence-model-1.recurrent-neural-netoworks.md)
- [自然语言处理与词嵌入](deep-learning/5.sequence-model-2.nlp-and-word-embeddings.md)
- [序列模型和注意力机制](deep-learning/5.sequence-model-3.sequence-models-and-attention-machanism.md)
6. 更多讨论(待补充)
1. [元学习(Meta learning)](deep-learning/6.meta-learning.md)
2. [Few-shot / Zero-shot learning](deep-learning/6.few-shot-learning.md)
3. 网络压缩
4. <img src="img/bilibili32.png" width="18" /> [GAN网络](https://www.bilibili.com/video/BV1rb4y187vD)
5. <img src="img/bilibili32.png" width="18" /> [Transformer](https://www.bilibili.com/video/BV1pu411o7BE)
6. <img src="img/bilibili32.png" width="18" /> [对比学习](https://www.bilibili.com/video/BV19S4y1M7hm)
### 深度学习框架:PyTorch
修订这段文字的时候已经是2023年,PyTorch无论是在工业界还是学术界,都已经碾压了其他的框架,例如TensorFlow、Keras。如果是入坑不久的朋友,我建议你直接学PyTorch就好了。其他框架基本上可以仅follow up即可。
* [<img src="img/bilibili32.png" width="18" /> PyTorch视频集合(32集)](https://www.bilibili.com/video/BV197411Z7CE/)
* [<img src="img/zhihu32.png" width="18" /> PyTorch的安装与Tutorial](https://zhuanlan.zhihu.com/p/60526007)
* [<img src="img/github32.png" width="18" /> PyTorch 中文手册](https://github.com/zergtant/pytorch-handbook)
* [PyTorch 官网的Tutorial](https://pytorch.org/tutorials/)
### 分布式训练
* [<img src="img/zhihu32.png" width="18" />《分布式训练》](https://zhuanlan.zhihu.com/p/129912419)
## 大模型
综述:[<img src="img/zhihu32.png" width="18" /> 2022 年中回顾 | 大模型技术最新进展](https://zhuanlan.zhihu.com/p/545709881?theme=dark)
### LLM 语言大模型
语言大模型(LLM)可以通
没有合适的资源?快使用搜索试试~ 我知道了~
精品--机器学习、深度学习的学习路径及知识总结.zip
![preview](https://csdnimg.cn/release/downloadcmsfe/public/img/white-bg.ca8570fa.png)
共130个文件
png:50个
md:43个
ipynb:17个
![preview-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/scale.ab9e0183.png)
需积分: 5 0 下载量 35 浏览量
2024-02-05
17:51:29
上传
评论
收藏 4.6MB ZIP 举报
温馨提示
精品--机器学习、深度学习的学习路径及知识总结
资源推荐
资源详情
资源评论
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![doc](https://img-home.csdnimg.cn/images/20210720083327.png)
收起资源包目录
![package](https://csdnimg.cn/release/downloadcmsfe/public/img/package.f3fc750b.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/HTML.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/JPG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/JPG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PDF.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
共 130 条
- 1
- 2
资源评论
![avatar-default](https://csdnimg.cn/release/downloadcmsfe/public/img/lazyLogo2.1882d7f4.png)
![avatar](https://profile-avatar.csdnimg.cn/3d2aa261f1ab4ec58f4e889756c93c5f_weixin_44976692.jpg!1)
![avatar-vip](https://csdnimg.cn/release/downloadcmsfe/public/img/user-vip.1c89f3c5.png)
码农阿豪
- 粉丝: 1w+
- 资源: 1755
上传资源 快速赚钱
我的内容管理 展开
我的资源 快来上传第一个资源
我的收益
登录查看自己的收益我的积分 登录查看自己的积分
我的C币 登录后查看C币余额
我的收藏
我的下载
下载帮助
![voice](https://csdnimg.cn/release/downloadcmsfe/public/img/voice.245cc511.png)
![center-task](https://csdnimg.cn/release/downloadcmsfe/public/img/center-task.c2eda91a.png)
安全验证
文档复制为VIP权益,开通VIP直接复制
![dialog-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/green-success.6a4acb44.png)