My notes and code that I wrote while taking Andrew Ng's Machine Learning course on Coursera. Or, more specifically, the notes are entirely hand-written by me, but most of the code was already prepared beforehand. I've been meaning to take this course for a while now, and I finally see why it's so acclaimed. It definitely helped me strengthen my foundational knowledge of machine learning.
Week 1: Supervised learning, linear regression, cost function, gradient descent.
Week 2: Multivariate linear regression, feature scaling, mean normalization, learning rate, the Normal Equation.
Week 3: Logistic regression, linear/non-linear decision boundaries, binary/multiclass classification, overfitting, regularization.
Week 4: Neural networks, logical operators, one-vs-all, non-linear classification.
Week 5: Forward propagation, backpropagation, random initialization.
Week 6: Precision/Recall, F1 score, bias/variance, trainining/validation/testing split.
Week 7: Support vector machines, kernels.
Week 8: Unsupervised learning, K-means clustering, dimensionality reduction, principal component analysis.
Week 9: Anomaly detection, content-based recommender systems, collaborative filtering recommender systems.
Week 10: Stochastic gradient descent, mini-batch gradient descent, online/continuous learning, map-reduce.
Week 11: Photo OCR, artificial data synthesis, ceiling analysis.