07.11.2024

# Linear Algebra and Feature Selection

with
Aleksandar Samsiev
and
Ivan Manov

Build the fundamental and practical linear algebra skills needed to become a data scientist and work on machine learning models and AI

3 hours of content
4084 students

Start for free

What you get:

- 3 hours of content
- 41 Interactive exercises
- 7 Downloadable resources
- World-class instructor
- Closed captions
- Q&A support
- Future course updates
- Course exam
- Certificate of achievement

# Linear Algebra and Feature Selection

A course by
Aleksandar Samsiev
and
Ivan Manov

Start for free

What you get:

- 3 hours of content
- 41 Interactive exercises
- 7 Downloadable resources
- World-class instructor
- Closed captions
- Q&A support
- Future course updates
- Course exam
- Certificate of achievement

Start for free

What you get:

- 3 hours of content
- 41 Interactive exercises
- 7 Downloadable resources
- World-class instructor
- Closed captions
- Q&A support
- Future course updates
- Course exam
- Certificate of achievement

## What You Learn

- Understand the math behind machine learning models
- Master key linear algebra concepts and theories for advanced mathematical applications
- Perform Principal Component Analysis (PCA) and Dimensionality Reduction in Python to simplify complex datasets for better analysis
- Learn to operate with eigenvalues and eigenvectors
- Apply theoretical math knowledge into practice to solve real-world problems through quantitative analysis
- Understand why linear algebra is useful

## Top Choice of Leading Companies Worldwide

Industry leaders and professionals globally rely on this top-rated course to enhance their skills.

## Course Description

Linear Algebra and Feature Selection is the course that provides you with the knowledge you need to grasp the math processes behind the machine learning algorithms for dimensionality reduction. Mastering the fundamentals of linear algebra will help you develop in-demand practical skills, such as building your own algorithms or choosing the most appropriate existing ones for a specific task you need to solve. The techniques you will learn - feature extraction and feature selection will enable you to handle high-dimensional data efficiently. In addition, you will get familiar with the mathematical concepts behind PCA and LDA, and practice applying these types of analysis using the corresponding Python libraries.

## Learn for Free

1.1 What Does the Course Cover

1.2 Why Linear Algebra?

1.3 Solving Quadratic Equations

1.4 Vectors

1.5 Matrices

1.7 The Transpose of Vectors and Matrices, the Identity Matrix

## Interactive Exercises

Practice what you've learned with coding tasks, flashcards, fill in the blanks, multiple choice, and other fun exercises.

Practice what you've learned with coding tasks, flashcards, fill in the blanks, multiple choice, and other fun exercises.

## Curriculum

- 1. Linear Algebra Essentials15 Lessons 77 Min
Here, we’ll cover the linear algebra concepts behind the machine learning algorithms for dimensionality reduction. We'll learn about vectors and matrices, linear equations, eigenvalues and eigenvectors, and more.

What Does the Course Cover4 minWhy Linear Algebra?4 minSolving Quadratic Equations Read now1 minVectors5 minMatrices4 minThe Transpose of Vectors and Matrices, the Identity Matrix4 minLinear Independence and Linear Span of Vectors7 minBasis of a Vector Space, Determinant of a Matrix, Inverse of a Matrix10 minSolving Equations of the Form A*x=b6 minThe Gauss Method7 minOther Solutions to the Equation A*x=b8 minDetermining Linear Independence of a Random Set of Vectors4 minEigenvalues and Eigenvectors3 minCalculating Eigenvalues4 minCalculating Eigenvectors6 min - 2. Dimensionality Reduction Motivation2 Lessons 7 Min
This section explains the intricacies of the dimensionality reduction process and clarifies why this technique is essential when working with large datasets.

Feature Selection, Feature Extraction, and Dimensionality Reduction4 minThe Curse of Dimensionality3 min - 3. Principal Component Analysis (PCA)4 Lessons 31 Min
In this part of the course, we explore the Principal Component Analysis (PCA) - one of the most widely used algorithms for dimensionality reduction. We'll demonstrate a practical example combining both feature extraction and feature selection techniques to achieve the desired goal - reducing the number of dimensions in our dataset.

Principal Component Analysis – Overview7 minA Step-by-Step Explanation of PCA on California Estates – Example12 minThe Theory Behind PCA5 minPCA Covariance Matrix in Jupyter – Analysis and Interpretation7 min - 4. Linear Discriminant Analysis (LDA)11 Lessons 60 Min
In this section, we'll cover another dimensionality reduction technique called Linear Discriminant Analysis (LDA). Here, we'll go through another practical example, showing the methodology behind LDA and its efficiency. We'll also make a comparison between this algorithm and PCA, introducing the advantages of both approaches.

Overall Mean and Class Means3 minLinear Discriminant Analysis – Overview4 minLDA: Calculating Within- and Between-Class Scatter Matrices9 minA Step-by-Step Еxplanation of LDA on a Wine Quality Dataset – Example6 minCalculating the Within- and Between-Class Scatter Matrices4 minCalculating Eigenvectors and Eigenvalues for the LDA7 minAnalysis of LDA3 minLDA vs. PCA5 minSetting Up the Classifier to Compare LDA and PCA5 minCoding the Classifier for LDA and PCA6 minAnalysis of the Training and Testing Times for the Classifier and Its Accuracy8 min

## Topics

## Course Requirements

- You need to complete an introduction to Python before taking this course
- Basic skills in statistics, probability, and linear algebra are required
- It is highly recommended to take the Machine Learning in Python course first

## Who Should Take This Course?

Level of difficulty: Intermediate

- People who want to improve their math for data science
- Aspiring data analysts, data scientists, business analysts
- Graduate students who need linear algebra and calculus for their studies

## Exams and Certification

A 365 Data Science Course Certificate is an excellent addition to your LinkedIn profile—demonstrating your expertise and willingness to go the extra mile to accomplish your goals.

## Meet Your Instructor

Aleksandar has a Bachelor's in Mathematics from the University of Bath (England), where he graduated with honors. He discovered a true passion in artificial intelligence, and believes that “a firm grasp of Linear Algebra is fundamental for understanding and developing concepts in the machine learning field”. In 2021, Aleksandar authored our Linear Algebra and Feature Selection course, while also contributing to the creation process of exam questions for the 365 Data Science Program. In his spare time, Aleksandar is an avid football supporter and a keen swimmer with 8 years of national-level competitive swimming under his belt.

## What Our Learners Say

## 365 Data Science Is Featured at

Our top-rated courses are trusted by business worldwide.