The math behind machine learning without fear: linear algebra, calculus and gradients, probability and statistics, and optimization, explained visually and coded in Python with NumPy.
Course Curriculum
| 1. Linear Algebra | |||
| 1.1 Vectors and vector operations | 00:12:00 | ||
| 1.2 Matrices and matrix multiplication | 00:12:00 | ||
| 1.3 Linear transformations | 00:10:00 | ||
| 1.4 Eigenvalues, eigenvectors and PCA intuition | 00:14:00 | ||
| 2. Calculus | |||
| 2.1 Derivatives and what they mean | 00:12:00 | ||
| 2.2 Partial derivatives and gradients | 00:12:00 | ||
| 2.3 The chain rule and backpropagation intuition | 00:12:00 | ||
| 3. Probability for ML | |||
| 3.1 Random variables and distributions | 00:10:00 | ||
| 3.2 Bayes theorem in machine learning | 00:10:00 | ||
| 3.3 Maximum likelihood | 00:10:00 | ||
| 4. Optimization | |||
| 4.1 Cost functions | 00:09:00 | ||
| 4.2 Gradient descent from scratch | 00:14:00 | ||
| 4.3 Final project: linear regression from scratch in NumPy | 00:22:00 | ||
Course Reviews
No Reviews found for this course.






Up Academy Data & AI Team