English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 1h 20m | 330 MB
Ever wondered what’s really going on underneath a machine learning algorithm? The answer is linear algebra. Without it, machine learning can’t exist. Linear algebra is a prerequisite for understanding and creating nearly all machine learning algorithms, especially those that prop up neural networks, natural language processing tools, and deep learning models.
Join instructor Terezija Semenski for an in-depth exploration of the core concepts of linear algebra alongside the techniques needed to design and implement a successful machine learning algorithm. Discover the basics of vector arithmetic, vector norms, matrix properties, advanced operations, matrix transformation, and algorithms like Google PageRank. By the end of this course, you’ll be ready to take the principles of linear algebra and apply them to your next big machine learning project.
Table of Contents
Introduction
1 Introduction
2 What you should know
Introduction to Linear Algebra
3 Defining linear algebra
4 Applications of linear algebra in ML
Vectors Basics
5 Introduction to vectors
6 Vector arithmetic
7 Coordinate system
Vector Projections and Basis
8 Dot product of vectors
9 Scalar and vector projection
10 Changing basis of vectors
11 Basis, linear independence, and span
Introduction to Matrices
12 Matrices introduction
13 Types of matrices
14 Types of matrix transformation
15 Composition or combination of matrix transformations
Gaussian Elimination
16 Solving linear equations using Gaussian elimination
17 Gaussian elimination and finding the inverse matrix
18 Inverse and determinant
Matrices from Orthogonality to Gram–Schmidt Process
19 Matrices changing basis
20 Transforming to the new basis
21 Orthogonal matrix
22 Gram–Schmidt process
Eigenvalues and Eigenvectors
23 Introduction to eigenvalues and eigenvectors
24 Calculating eigenvalues and eigenvectors
25 Changing to the eigenbasis
26 Google PageRank algorithm
Conclusion
27 Next steps
Resolve the captcha to access the links!