# ML-Tutorial-Experiment **Repository Path**: prg/ML-Tutorial-Experiment ## Basic Information - **Project Name**: ML-Tutorial-Experiment - **Description**: Coding the Machine Learning Tutorial for Learning to Learn - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-08-23 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # ML-Tutorial-Experiment Coding the Machine Learning Tutorial for Learning to Learn - 第一期：[从零开始用TensorFlow搭建卷积神经网络](https://www.jiqizhixin.com/articles/2017-08-29-14)--&--[文章代码](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_CNN_Tutorial.ipynb) - 补充资料：[基础代码解析](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_trial_1.ipynb) - 补充资料：[Keras构建CNN](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_Keras_CNN.ipynb) - 补充资料：[TensorFlow构建LeNet-5](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_LeNet5.ipynb) - 补充资料：[从DensNet到CliqueNet，探索卷积神经网络架构](https://www.jiqizhixin.com/articles/2018-05-23-6) - 第二期：[GAN完整理论推导与实现](https://www.jiqizhixin.com/articles/2017-10-1-1)--&--[文章代码](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/Keras_GAN.ipynb) - 补充资料：[原版GAN的TensorFlow实现](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_GAN.ipynb) - 第三期：[CapsNet结构解析与实现](https://www.jiqizhixin.com/articles/2017-11-05)--&--[文章代码](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/tf_orginal_CapsNet.ipynb) - 补充资料：[解读官方实现的核心代码](https://www.jiqizhixin.com/articles/capsule-implement-sara-sabour-Feb02) - 第四期：[RNN与CNN的序列建模](https://www.jiqizhixin.com/articles/2018-04-12-3)--&--[LSTM语言建模](https://github.com/jiqizhixin/ML-Tutorial-Experiment/blob/master/Experiments/LSTM_PTB.ipynb)--&--[TCN官方实现](https://github.com/locuslab/TCN)--&--[TCN语言建模（Colaboratory）](https://colab.research.google.com/drive/1GAXC0j9qzLyQu8G9_P_eHi-TtYm7uhXF) - 第五期：[基于Transformer的神经机器翻译](https://www.jiqizhixin.com/articles/Synced-github-implement-project-machine-translation-by-transformer)--&--[Colaboratory实现](https://colab.research.google.com/drive/1Wt9Jwynnki6lipwUcy0Sz5WKG7MYSGs0) # ------ 为了扩展优秀模型与实现，机器之心将梳理历史优质文章，同时也欢迎各位开发者与研究者提供优质的文章。我们将尝试确定添加的文章都是可复现，且基本无理解性错误的文章，并按以下模型归类。若读者发现这些文章有错误或理解误差，可以在 GitHub 上提 issue，确定后我们将修改文章。 * 数学与编程基础 * 线性代数 * [教程 | 基础入门：深度学习矩阵运算的概念和代码实现](https://www.jiqizhixin.com/articles/2017-08-07-2) * 概率与信息论 * [从概率论到多分类问题：综述贝叶斯统计分类](https://www.jiqizhixin.com/articles/2017-09-28) * 数值计算 * Python基础 * [从变量到封装：一文带你为机器学习打下坚实的Python基础](https://www.jiqizhixin.com/articles/2017-10-13) * [一文带你了解 Python 集合与基本的集合运算](https://www.jiqizhixin.com/articles/062403) * NumPy基础 * [搭建模型第一步：你需要预习的 NumPy 基础都在这了](https://www.jiqizhixin.com/articles/070101) * [从数组到矩阵的迹，NumPy常见使用大总结](https://www.jiqizhixin.com/articles/2017-10-28) * [数据科学初学者必知的NumPy基础知识](https://www.jiqizhixin.com/articles/2018-04-21-7) * 一般机器学习 * 入门模型 * 线性回归 * [初学TensorFlow机器学习：如何实现线性回归？](https://www.jiqizhixin.com/articles/2017-05-14-2) * [Python环境下的8种简单线性回归算法](https://www.jiqizhixin.com/articles/2018-01-01) * [极简Python带你探索分类与回归的奥秘](https://www.jiqizhixin.com/articles/03132) * Logistic 回归 * [从原理到应用：简述Logistics回归算法](https://www.jiqizhixin.com/articles/2018-05-13-3) * [从头开始：用Python实现带随机梯度下降的Logistic回归](https://www.jiqizhixin.com/articles/2017-02-17-5) * 朴素贝叶斯 * [实践中最广泛应用的分类模型：朴素贝叶斯算法](https://www.jiqizhixin.com/articles/033088) * 决策树 * 支持向量机 * 聚类方法 * K均值聚类 * 层次聚类 * 降维算法 * PCA * 自编码器 * t-SNE * 集成方法 * Staking * Bagging * 随机森林 * Boosting * AdaBoost * 提升树 * 梯度提升树 * 概率图模型 * 隐马尔科夫模型 * 隐马尔可夫随机场 * 条件随机场 * 半监督学习 * Entropy-based * Graph-based * 深度学习 * 最优化方法 * 深度前馈网络 * 深度卷积网络 * 深度循环网络 * 深度生成模型 * PixelRNN/PixelCNN * VAE * GAN