Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Dive into the second half of linear algebra coding exercises in this 43-minute video tutorial. Work through practical applications of linear algebra in machine learning, including shape-checking as type-checking, matrix composition, and matrix multiplication as a for loop. Explore concepts like matrices as batches of vectors, concatenating matrices for parallel programming, and creating matrix repeaters. Gain insights into the two fundamental views of matrices in machine learning while completing hands-on exercises. Access the exercise notebook and related resources to practice alongside the instructors and deepen your understanding of linear algebra's role in ML programming.
Syllabus
- Teaser
- Intro
- Linear algebra as programming
- Exercise: Shape-checking as type-checking
- Exercise: Composing two matrices
- Exercise: Composing four matrices
- Matrix multiplication as a for loop
- Exercise: Matrices as batches of vectors
- Concatenating matrices as parallel programming
- Exercise: make_repeater
- The two views of matrices in ML
- Outro
Taught by
Weights & Biases