Mathematical Foundations of Data Science
IIITH
Enrollment is Closed
Foundations:
Estimation from Random Samples and Confidence Intervals, Random Walks in Graphs and PageRank, Best fit subspace or PCA using SVD.Algorithms for Large Datasets:
Streaming Algorithms, Property testing, Hashing, Approximate Nearest Neighbours using Locality Sensitive HashingTheory of Supervised Learning:
PAC Learning, Sample Complexity, VC Dimension, Learning Half spaces, JuntasRequirements
Linear Algebra, Probability, Discrete Mathematics.