DeqianBai / Hands On Machine Learning
Licence: apache-2.0
A series of Jupyter notebooks with Chinese comment that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
Stars: ✭ 1,363
Labels
Projects that are alternatives of or similar to Hands On Machine Learning
Facedetector
A re-implementation of mtcnn. Joint training, tutorial and deployment together.
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Mv3d tf
Tensorflow implementation of Multi-View 3D Object Detection Network (in progress)
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Bayarea Dl Summerschool
Torch notebooks and slides for the Bay Area Deep Learning Summer School
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Ml Sound Classifier
Machine Learning Sound Classifier
Stars: ✭ 98 (-92.81%)
Mutual labels: jupyter-notebook
Btctrading
Time Series Forecast with Bitcoin value, to detect upward/down trends with Machine Learning Algorithms
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Afnet
Code for paper in CVPR2019, 'Attentive Feedback Network for Boundary-aware Salient Object Detection'
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Advisor
Open-source implementation of Google Vizier for hyper parameters tuning
Stars: ✭ 1,359 (-0.29%)
Mutual labels: jupyter-notebook
Organic
Code repo for optimizing distributions of molecules.
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Deeplearning
Python implementation of Deep Learning book
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Ucl Deep Learning Ans Reinforcement Learning
Deep learning and Reinforcement learning lecture and course work
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Math of machine learning
This is the code for "Mathematcs of Machine Learning" by Siraj Raval on Youtube
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Libpysal
Core components of Python Spatial Analysis Library
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Adversarially Learned Anomaly Detection
ALAD (Proceedings of IEEE ICDM 2018) official code
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Junosautomation
To contain example scripts for different tools.
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Bds
Code and examples from Business Data Science
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Pyspark Predictive Maintenance
Predictive Maintenance using Pyspark
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Neural Tangents
Fast and Easy Infinite Neural Networks in Python
Stars: ✭ 1,357 (-0.44%)
Mutual labels: jupyter-notebook
Quant at
Python version of Dr. Ernie Chan's Matlab code and some inspired from Robert Carver's, plus some raw data downloaders
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Noisy labels
TRAINING DEEP NEURAL-NETWORKS USING A NOISE ADAPTATION LAYER
Stars: ✭ 99 (-92.74%)
Mutual labels: jupyter-notebook
Hands-on-Machine-Learning
目的
这份笔记旨在帮助中文学习者以一种较快较系统的方式入门机器学习，
是在学习Hands-on Machine Learning with Scikit-Learn and TensorFlow这本书的 时候做的个人笔记:
此项目的可取之处
- 原书的代码示例部分只有代码没有文字注释，纸质书上有文字解释但不利于操作，这个项目将其合二为一， 学习者这只需要打开Jupyter notebook即可，无需频繁翻阅纸质书籍或查看PDF文档
- 形式和吴大大Deep learning.ai课程作业的形式一样，一段文字解释，一段代码操作，方便快速理解原理并进行实践操作
- 中文注释，方便中文学习者较快较系统的入门机器学习
说明
- 全书分为 Part I 机器学习(8 章) 和 Part II 深度学习(8 章) 两大部分，Part II 最后一章是强化学习
- 绪论部分和第一章大家直接看原书就好了，这个项目的代码示例是从第二章开始的
- 此项目适用于英语不是那么好，而且时间又不怎么充裕，又想要快速入门机器学习的读者，大神就不要在这里耽误时间， 当然你如果想要完善一下自己的知识体系，缕清一些概念之间的关系，这本书还是很不错的选择
建议
- 关于时间，这本书是一位美国数据科学家向我推荐的，他从头到尾做完了整本书的所有示例代码，大概用了80个小时左右，以此作为参考，大家自行安排自己的进度
- 关于习题，每一章后面都提供了相应的练习题，既有简述类的问答题，也有任务型的代码操作题，附录里面都有参考答案，建议有时间的都学习一下，对于掌握知识，应对面试，很有帮助。简述型的课后习题都以章节为单位翻译成中文放在我的简书上了欢迎查阅Hands-on machine learning with scikit-learn and tensorflow
收获
- 在知识点广度上扫清一系列机器学习和深度学习的概念，循序渐进，易于接受
- 第二章使用Scikit-Learn 全程跟踪一个机器学习项目的例子，非常有帮助
- 探索各种训练模型，包括：支持向量机、决策树、随机森林以及集成方法
- 使用TensorFlow库构建和训练神经网络，深入神经网络架构，包括卷积神经网络、循环神经网络和深度强化学习
- 知识体系非常系统， 如果你能够从绪论部分一直看到附录部分并做完这上面的示例代码，你的理论基础一定会扎实的不要不要的
感谢
- 感谢Aurelien Geron，这是一本非常优秀的教材 Hands-on Machine Learning with Scikit-Learn and TensorFlow
- 感谢 Will Koehrsen，是他向我推荐了这本书
联系我
如果你有任何问题可以邮件联系我
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].