Introduction to Machine Learning
Start by reading the tips below. I've included some lecture-related tips in a post. Note that for a proof-based course like this one, it's more important than ever to understand how a lecture relates to the rest of the content.
I've made some explainer courses, which contain guided practice. Use these for more practical guidance.
Here are resources per topic in the course. After lecture, review the associated crib sheet, and take a quiz with an exam mindset. The notes below are organized using a mixture of different semesters, as each semester's topic coverage and ordering can vary.
- Abstractions Note
- Perceptrons Note QuizSol
- Support Vector Machines Note Quiz Sol
- Convex Optimization Note
- Decision Theory Note
- Discriminant Analysis: LDA, QDA Note Crib QuizSol
- Decompositions: EVD, SVD Note SVD
- Least Squares Note Slides Crib QuizSol
- Ridge Regression Note Slides Crib QuizSol
- Logistic Regression Note
- Bias-Variance Note Crib QuizSol
- Cross Validation Note
- Weighted, Total Least Squares Crib
- Principal Component Analysis Note Crib
- Canonical Correlation Analysis Note
- Nonlinear Least Squares, Gradient Descent Crib
- Neural Networks Note
- Convolutional Neural Networks Note
- Kernels Note
- Nearest Neighbors Note
- Randomized Decision Trees - Note #1 - Note #2
- Clustering Note
Here was the start of a cheat sheet I was assembling, to summarize the decisions associated with machine learning in the wild. Make sure the concepts included here are familiar.
Here are additional notes for special topics from guest lectures or one-off topics specific to a semester.
- Fairness in Machine Learning
- Neural Networks : Inspiration in Biology
- Clustering with Gradient Descent
- Kernelized Algorithms
- Kullback-Leibler Divergence
- Closing Remarks from Fall 2016
That's it for this course guide. For your final exams, practice proofs and recall takeaways using the crib sheets above. Good luck!
Want more tips? Drop your email, and I'll keep you in the loop.