machine-learning-visualized is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named machine-learning-visualized among their alternatives. The relationship is not symmetric — how machine-learning-visualized rates them is a separate judgement, made when machine-learning-visualized is analysed in its own right.
calls machine-learning-visualized “Choose for current, visually rich notebooks with first-principles derivations.”
🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
calls machine-learning-visualized “Choose for a current, first-principles notebook treatment of ML algorithms instead of the outdated book code.”
The "Python Machine Learning (1st edition)" book code repository and info resource
calls machine-learning-visualized “For NumPy-only derivations that emphasize mathematical detail.”
A resource for learning about Machine learning & Deep Learning
calls machine-learning-visualized “choose for mathematical first-principles implementations with NumPy instead of a high-level scikit-learn challenge.”
100 Days of ML Coding
calls machine-learning-visualized “choose for visual, from-scratch derivations of ML algorithms; seed is broader”
Python Data Science Handbook: full text in Jupyter Notebooks
calls machine-learning-visualized “Choose when you want first-principles derivations and visualizations in NumPy instead of TensorFlow-specific code.”
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
calls machine-learning-visualized “Choose when you want algorithms explained from first principles with NumPy instead of sklearn/TensorFlow.”
⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.
calls machine-learning-visualized “choose when you prefer Jupyter notebooks with visualizations and first-principles derivations over standalone scripts.”
Minimal and clean examples of machine learning algorithms implementations
calls machine-learning-visualized “when you want first-principles derivations and visualizations of ML algorithms in notebooks.”
Open Machine Learning Course
calls machine-learning-visualized “When you want ML algorithms derived from first principles and visualized in notebooks, great for intuition.”
A collection of machine learning examples and tutorials.
calls machine-learning-visualized “First-principles NumPy ML derivations; choose for mathematical depth over the seed's tutorial survey.”
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
calls machine-learning-visualized “Use it when you want NumPy first-principles derivations of core ML algorithms, not the seed's wider CS/math/AI scope.”
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
calls machine-learning-visualized “When you only need classical ML algorithms and want NumPy-based derivations in notebooks, without deep learning.”
AI实战-practicalAI 中文版