Machine learning education / coding challenge
A 100-day machine learning coding challenge that provides daily tutorials, code examples, and infographics for core ML algorithms using Python and scikit-learn.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose for TensorFlow-based, runnable ML/DL examples rather than a scikit-learn 100-day challenge.
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
choose to study minimal, clean implementations of algorithms instead of a guided daily challenge.
Minimal and clean examples of machine learning algorithms implementations
choose for a broad, video-backed collection of ML/DL tutorials instead of a fixed-day plan.
A resource for learning about Machine learning & Deep Learning
choose for a structured Chinese-language PyTorch AI course instead of a 100-day challenge.
AI实战-practicalAI 中文版
choose for mathematical first-principles implementations with NumPy instead of a high-level scikit-learn challenge.
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy
choose for a structured open course with assignments and a wider curriculum instead of a daily challenge.
Open Machine Learning Course
choose to read plain-Python implementations of basic algorithms without following a daily schedule.
Plain python implementations of basic machine learning algorithms
choose for the modern Hands-On ML book notebooks using Scikit-Learn, Keras, and TF; a comprehensive alternative.
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries.
choose for project-based notebook examples to learn ML by building mini projects.
This repository contains mini projects in machine learning with notebook files
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose for Raschka's older classification-focused notebooks if you need deep-dive classification tutorials.
A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks
choose for scikit-learn-specific video-based notebooks; narrower and older.
Jupyter notebooks from the scikit-learn video series
choose for a PyTorch-specific handbook; narrower framework coverage than the seed.
pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行
choose for the code from the old 1st edition of the Python ML book; a previous-generation resource.
The "Python Machine Learning (1st edition)" book code repository and info resource
choose for a university-style deep-learning (Keras) course; narrower focus on neural networks.
T81-558: Keras - Applications of Deep Neural Networks @Washington University in St. Louis
A 50-day challenge in the same format, but unmaintained for 6+ years.
A day to day plan for this challenge (50 Days of Machine Learning) . Covers both theoretical and practical aspects
Aged code collection of ML algorithm implementations, lacking structured explanations.
Implementation of Machine Learning Algorithms
Older NumPy implementation collection in Chinese; useful but unmaintained.
:star2:【Numpy 手写实现】SVM 支持向量机 | KNN K近邻 | Kmeans | Logistic Regression 逻辑回归 | Maximum Entropy 最大熵 | Naive Bayes 朴素贝叶斯 | Perception 感知机 | Decision Tree 决策树 | Random Forest 随机森林 | DBDT | GDA 高斯判别分析 | PCA 主成分分析 | LDA 线性判别分析
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
interactive web articles for learning ML; not a code repository to integrate.
Visual, Interactive Articles About Machine Learning: https://mlu-explain.github.io/
These projects were analysed and named 100-Days-Of-ML-Code among their alternatives. The relationship is not symmetric — how 100-Days-Of-ML-Code rates them is a separate judgement, made when 100-Days-Of-ML-Code is analysed in its own right.
calls 100-Days-Of-ML-Code “Choose for a code-first, challenge-based introduction to ML rather than a Q&A review; it is lighter on theory.”
深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06
calls 100-Days-Of-ML-Code “Choose this when you want a structured daily code challenge in English over course notes.”
吴恩达老师的机器学习课程个人笔记
calls 100-Days-Of-ML-Code “Choose for a structured 100-day learning challenge with code snippets.”
🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
calls 100-Days-Of-ML-Code “Choose for a quick daily-coding challenge rather than a structured book.”
The "Python Machine Learning (1st edition)" book code repository and info resource
calls 100-Days-Of-ML-Code “For a structured 100-day ML code challenge with a different learning path and broader examples.”
:zap:机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归
calls 100-Days-Of-ML-Code “Choose for a simple, day-by-day challenge format, but it is outdated and not TensorFlow-based.”
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
calls 100-Days-Of-ML-Code “Older 100-day code drill covering common ML algorithms with shallow explanations; useful for beginners wanting a daily challenge, but less complete and stale.”
AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2
calls 100-Days-Of-ML-Code “choose if you need the original English version, but it's not been updated in years.”
100-Days-Of-ML-Code中文版
calls 100-Days-Of-ML-Code “when you want a quick, code-snippet-based crash course and can accept a stale, less rigorous resource.”
Open Machine Learning Course
calls 100-Days-Of-ML-Code “For a famous beginner coding challenge, though outdated.”
A resource for learning about Machine learning & Deep Learning
calls 100-Days-Of-ML-Code “When you want a very rudimentary, challenge-style ML code path; it is not deep or comprehensive compared to the seed.”
AI实战-practicalAI 中文版