Topic Course in Machine Learning for Big Data
This is jupyter notebook for MAT810 Advanced Topics in Machine Learning Course at SUNY Albany.
In Spring 2022, I mainly focus on unsupervised learning on big data. Many algorithms actually need to be modified to accommodate large dataset or large dimensions. All brute force methods will fail miserably, either runs out of memory or takes way too much time of computation. I introduce the algorithms, explain the mathematical details and implement them from scratch mostly only using numpy/scipy.