Mathematics of Machine Learning
Computing & Data Science
The rigorous mathematical foundations of machine learning: optimization, statistical learning theory, kernel methods, neural networks, and PAC learning.
Learning Objectives
- Understand gradient descent and convex optimization
- Apply statistical learning theory and VC dimension
- Work with kernels and the kernel trick
- Analyze neural networks mathematically
- Understand PAC learning bounds
- Apply information-theoretic learning bounds
Lessons
1
Convex Optimization & Gradient Descent
42 min
2
Stochastic Gradient Descent & Convergence
42 min
3
Statistical Learning Theory: Risk & Generalization
42 min
4
VC Dimension & PAC Learning
42 min
5
Kernel Methods & Reproducing Kernel Hilbert Spaces
42 min
6
Support Vector Machines: Primal & Dual
42 min
7
Neural Networks: Universal Approximation & Backpropagation
42 min
8
Regularization: Ridge, Lasso & Bayesian Perspective
42 min
9
Dimensionality Reduction: PCA, SVD & Manifold Learning
42 min
10
Information Theory in ML: MDL, Mutual Information & Compression
42 min
Quick Practice
Test your knowledge with a quick interactive challenge from this module.
Loading…
Score:
0/0
Key Concept Flashcards
Loading…
1 / 1
Click the card to flip it