Machine-Learning-Specialization-Coursera and deep-learning-coursera
These are competitors—both provide complete solution sets and notes for the same Coursera Deep Learning Specialization, so users would typically choose one repository over the other rather than use them together.
About Machine-Learning-Specialization-Coursera
greyhatguy007/Machine-Learning-Specialization-Coursera
Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG
Organizes three specialization courses into structured Jupyter notebooks covering linear/logistic regression, neural networks, and unsupervised learning with hands-on labs implementing algorithms using NumPy, scikit-learn, and TensorFlow. Each week includes practice quizzes, optional labs demonstrating core concepts (gradient descent, vectorization, feature scaling), and graded programming assignments with complete solutions. The implementation emphasizes vectorized NumPy operations and comparison between manual gradient descent implementations and scikit-learn's optimized solvers.
About deep-learning-coursera
Kulbear/deep-learning-coursera
Deep Learning Specialization by Andrew Ng on Coursera.
Contains Jupyter notebooks implementing core deep learning concepts—from logistic regression and multi-layer perceptrons through CNNs (ResNets, Keras) and sequence models (RNNs)—alongside quiz materials across five course modules. Implementations use NumPy for foundational algorithms and TensorFlow/Keras for practical applications, covering optimization techniques (gradient descent, Adam), regularization, and batch normalization. Spans the full specialization curriculum from foundational neural network theory to advanced architectures for computer vision and natural language processing tasks.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work