Image by storyset on Freepik
When you’re learning data science, building a good foundation in math will make your learning journey easier and much more effective. Even if you’ve already landed your first data role, learning math fundamentals for data science will only take your skills further.
From exploratory data analysis to building machine learning models, having a good foundation in math topics like linear algebra and statistics will give you a better understanding of why you do what you do. So even if you are a beginner, this list of courses will help you learn:
- Basic math skills
- Calculus
- Linear Algebra
- Probability and Statistics
- Optimization
Sounds interesting, yes? Let’s get started!
Data science courses require you to be comfortable with math as a prerequisite. To be specific, most courses assume that you’re comfortable with high school algebra and calculus. But no worries if you are not there yet.
The Data Science Math Skills course, offered by Duke University on Coursera will help you get up and running with math fundamentals in as little time as possible. The topics covered in this course include:
- Problem solving
- Functions and graphs
- Intro to calculus
- Intro to probability
It’s recommended that you go through this course before you start the other courses that explore specific math topics in greater depth.
Link: Data Science Math Skills – Duke University on Coursera
When we talk about math for data science, calculus is definitely something you should be comfortable with. But most learners find high school calculus intimidating (I’ve been there, too!). This, however, is partly because of how we learn—mostly focusing on concepts, a small number of illustrative examples, and a ton of practice exercises.
But you’ll understand and learn calculus much better if there are helpful visualizations—to help go from intuition to equation—focusing on the why.
The Calculus course by Grant Sanderson of 3Blue1Brown is exactly what all of us need! Through a series of lessons with super helpful visualizations—going from geometry to formula wherever possible—this course will help you learn the following and more:
- Limits and derivatives
- Power rule, chain rule, product rule
- Implicit differentiation
- Higher order derivatives
- Taylor series
- Integration
Link: Calculus – 3Blue1Brown
As a data scientist, the datasets that you work are essentially matrices of dimensions num_samples x num_features. You can, therefore, think of each data point as a vector in the feature space. So understanding how matrices work, common operations on matrices, matrix decomposition techniques are all important.
If you loved the calculus course from 3Blue1Brown, you’ll probably enjoy the linear algebra course from Grant Sanderson just as much if not more. The Linear Algebra course from 3Blue1Brown will help you learn help you learn the following:
- Fundamentals of vectors and vector spaces
- Linear combinations, span, and basis
- Linear transformation and matrices
- Matrix multiplication
- 3D linear transformation
- Determinant
- Inverses, column space, and null space
- Dot and cross products
- Eigenvalues and eigenvectors
- Abstract vector spaces
Link: Linear Algebra – 3Blue1Brown
Statistics and probability are great skills to add to your data science toolbox. But they are by no means easy to master. However, it’s relatively easier to get your fundamentals down and build on them.
The Statistics and Probability course from Khan Academy will help you learn the probability and statistics you need to start working with data more effectively. Here is an overview of the topics covered:
- Analyzing categorical and quantitative data
- Modeling data distributions
- Probability
- Counting, permutations, and combinations
- Random variables
- Sampling distribution
- Confidence interval
- Hypothesis testing
- Chi-square test
- ANOVA
If you’re interested in diving deep into statistics, also check out 5 Free Courses to Master Statistics for Data Science.
Link: Statistics and Probability – Khan Academy
If you’ve ever trained a machine learning model, you know that the algorithm learns the optimal values of the parameters of the model. Under the hood, it runs an optimization algorithm to find the optimal value.
The Optimization for Machine Learning Crash Course from Machine Learning Mastery is a comprehensive resource to learn optimization for machine learning.
This course takes a code-first approach using Python. So after understanding the importance of optimization, you’ll write Python code to see popular optimization algorithms in action. Here’s an overview of the topics covered:
- The need for optimization
- Grid search
- Optimization algorithms in SciPy
- BFGS algorithm
- Hill climbing algorithm
- Simulated annealing
- Gradient descent
Link: Optimization for Machine Learning Crash Course – MachineLearningMastery.com
I hope you found these resources helpful. Because most of these courses are tailored towards beginners, you should be able to pick up all the essential math without feeling overwhelmed.
If you’re looking for courses to learn Python for data science, read 5 Free Courses to Master Python for Data Science.
Happy learning!
Bala Priya C is a developer and technical writer from India. She likes working at the intersection of math, programming, data science, and content creation. Her areas of interest and expertise include DevOps, data science, and natural language processing. She enjoys reading, writing, coding, and coffee! Currently, she’s working on learning and sharing her knowledge with the developer community by authoring tutorials, how-to guides, opinion pieces, and more. Bala also creates engaging resource overviews and coding tutorials.
