Calculus for Machine Learning and Data Science
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Calculus for Machine Learning and Data Science
This course is part of Mathematics for Machine Learning and Data Science Specialization
Instructor: Luis Serrano
93,698 already enrolled
Ask Coursera
963 reviews
Recommended experience
963 reviews
Recommended experience
What you'll learn
Analytically optimize different types of functions commonly used in machine learning using properties of derivatives and gradients
Approximately optimize different types of functions commonly used in machine learning
Visually interpret differentiation of different types of functions commonly used in machine learning
Perform gradient descent in neural networks with different activation and cost functions
Skills you'll gain
Tools you'll learn
Details to know
See how employees at top companies are mastering in-demand skills
Build your subject-matter expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate
There are 3 modules in this course
Newly updated for 2024! Mathematics for Machine Learning and Data Science is a foundational online program created by DeepLearning.AI and taught by Luis Serrano. In machine learning, you apply math concepts through programming. And so, in this specialization, you’ll apply the math concepts you learn using Python programming in hands-on lab exercises. As a learner in this program, you'll need basic to intermediate Python programming skills to be successful.
After completing this course, learners will be able to: • Analytically optimize different types of functions commonly used in machine learning using properties of derivatives and gradients • Approximately optimize different types of functions commonly used in machine learning using first-order (gradient descent) and second-order (Newton’s method) iterative methods • Visually interpret differentiation of different types of functions commonly used in machine learning • Perform gradient descent in neural networks with different activation and cost functions Many machine learning engineers and data scientists need help with mathematics, and even experienced practitioners can feel held back by a lack of math skills. This Specialization uses innovative pedagogy in mathematics to help you learn quickly and intuitively, with courses that use easy-to-follow visualizations to help you see how the math behind machine learning actually works. We recommend you have a high school level of mathematics (functions, basic algebra) and familiarity with programming (data structures, loops, functions, conditional statements, debugging). Assignments and labs are written in Python but the course introduces all the machine learning libraries you’ll use.
After completing this course, you will be able to:
What's included
28 videos7 readings2 assignments1 programming assignment1 ungraded lab2 plugins
28 videos•Total 116 minutes
- Course Introduction•4 minutes
- A note on programming experience•1 minute
- Machine Learning Motivation•7 minutes
- Motivation to Derivatives - Part I•7 minutes
- Derivatives and Tangents•2 minutes
- Slopes, maxima and minima•3 minutes
- Derivatives and their notation•2 minutes
- Some common derivatives - Lines•3 minutes
- Some common Derivatives - Quadratics•4 minutes
- Some common derivatives - Higher degree polynomials•3 minutes
- Some common derivatives - Other power functions•4 minutes
- The inverse function and its derivative•8 minutes
- Derivative of trigonometric functions•5 minutes
- Meaning of the Exponential (e)•9 minutes
- The derivative of e^x•3 minutes
- The derivative of log(x)•4 minutes
- Existence of the derivative•5 minutes
- Properties of the derivative: Multiplication by scalars•3 minutes
- Properties of the derivative: The sum rule•3 minutes
- Properties of the derivative: The product rule•4 minutes
- Properties of the derivative: The chain rule•5 minutes
- Introduction to optimization•4 minutes
- Optimization of squared loss - The one powerline problem•2 minutes
- Optimization of squared loss - The two powerline problem•4 minutes
- Optimization of squared loss - The three powerline problem•4 minutes
- Optimization of log-loss - Part 1•8 minutes
- Optimization of log-loss - Part 2•3 minutes
- Week 1 - Conclusion•1 minute
7 readings•Total 62 minutes
- Learning Python: Recommended Resources•10 minutes
- Join the DeepLearning.AI Forum to ask questions, get support, or share amazing ideas!•2 minutes
- Approximation of Derivatives•10 minutes
- (Optional) Downloading your Notebook and Refreshing your Workspace•10 minutes
- (Optional) Assignment Troubleshooting Tips•10 minutes
- (Optional) Partial Grading for Assignments•10 minutes
- Week 1 - Slides•10 minutes
2 assignments•Total 90 minutes
- Derivatives and Optimization•30 minutes
- Derivatives•60 minutes
1 programming assignment•Total 180 minutes
- Optimizing Functions of One Variable: Cost Minimization•180 minutes
1 ungraded lab•Total 60 minutes
- Differentiation in Python: Symbolic, Numerical and Automatic•60 minutes
2 plugins•Total 30 minutes
- Concept of Derivatives•15 minutes
- Common Derivatives•15 minutes
What's included
15 videos1 reading2 assignments1 programming assignment2 ungraded labs1 plugin
15 videos•Total 54 minutes
- Introduction to Tangent planes•3 minutes
- Partial derivatives - Part 1•5 minutes
- Partial derivatives - Part 2•2 minutes
- Gradients•2 minutes
- Gradients and maxima/minima•3 minutes
- Optimization with gradients: An example•7 minutes
- Optimization using gradients - Analytical method•7 minutes
- Optimization using Gradient Descent in one variable - Part 1•3 minutes
- Optimization using Gradient Descent in one variable - Part 2•5 minutes
- Optimization using Gradient Descent in one variable - Part 3•2 minutes
- Optimization using Gradient Descent in two variables - Part 1•1 minute
- Optimization using Gradient Descent in two variables - Part 2•5 minutes
- Optimization using Gradient Descent - Least squares•2 minutes
- Optimization using Gradient Descent - Least squares with multiple observations•5 minutes
- Week 2 - Conclusion•0 minutes
1 reading•Total 10 minutes
- Week 2 - Slides•10 minutes
2 assignments•Total 60 minutes
- Partial Derivatives and Gradient Descent•30 minutes
- Partial Derivatives and Gradient•30 minutes
1 programming assignment•Total 180 minutes
- Optimization Using Gradient Descent: Linear Regression•180 minutes
2 ungraded labs•Total 120 minutes
- Optimization Using Gradient Descent in One Variable•60 minutes
- Optimization Using Gradient Descent in Two Variables•60 minutes
1 plugin•Total 15 minutes
- Minimum, maximum and saddle points on surfaces•15 minutes
What's included
17 videos4 readings2 assignments1 programming assignment3 ungraded labs1 plugin
17 videos•Total 91 minutes
- Regression with a perceptron•5 minutes
- Regression with a perceptron - Loss function•3 minutes
- Regression with a perceptron - Gradient Descent•6 minutes
- Classification with Perceptron•6 minutes
- Classification with Perceptron - The sigmoid function•4 minutes
- Classification with Perceptron - Gradient Descent•5 minutes
- Classification with Perceptron - Calculating the derivatives•8 minutes
- Classification with a Neural Network•5 minutes
- Classification with a Neural Network - Minimizing log-loss•8 minutes
- Gradient Descent and Backpropagation•6 minutes
- Newton's Method•5 minutes
- Newton's Method: An example•3 minutes
- The second derivative•10 minutes
- The Hessian•5 minutes
- Hessians and concavity•6 minutes
- Newton's Method for two variables•5 minutes
- Week 3 - Conclusion•1 minute
4 readings•Total 27 minutes
- [IMPORTANT] Reminder about end of access to Lab Notebooks•2 minutes
- Week 3 - Slides•10 minutes
- Acknowledgments•10 minutes
- (Optional) Opportunity to Mentor Other Learners•5 minutes
2 assignments•Total 150 minutes
- Optimization in Neural Networks and Newton's Method•120 minutes
- Optimization in Neural Networks•30 minutes
1 programming assignment•Total 180 minutes
- Neural Network with Two Layers•180 minutes
3 ungraded labs•Total 180 minutes
- Regression with Perceptron•60 minutes
- Classification with Perceptron•60 minutes
- Optimization Using Newton's Method•60 minutes
1 plugin•Total 15 minutes
- Concept of Second Derivatives•15 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor
Offered by
Explore more from Algorithms
- D
DeepLearning.AI
Course
- D
DeepLearning.AI
Course
Why people choose Coursera for their career
Learner reviews
- 5 stars
85.47%
- 4 stars
10.16%
- 3 stars
2.28%
- 2 stars
1.14%
- 1 star
0.93%
Showing 3 of 963
Reviewed on Jan 3, 2025
It was a great learning experience, and all the examples were carefully chosen with a special focus on machine learning. Well done and thank you!
Reviewed on Jan 30, 2025
Very Good Course for Beginners that have no knowledge of mathematics but it makes harder when come to Lab. Everything is perfect but Labs are very Difficult to understand
Reviewed on Feb 27, 2023
This course refresh my knowledge about calculus back in senior high school and even it makes me understand better about calculus and apply it in machine learning.
Frequently asked questions
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.
More questions
Financial aid available,