인프런 - 라이프타임 커리어 플랫폼

This is a lecture that condenses the math content learned in middle and high school. You will learn the necessary mathematical knowledge and techniques for each item with a lot of practice.

This course is a course that practices the basics of machine learning mathematics and statistics using Python. Machine learning and deep learning require programming skills, but they also require a mathematical background to understand the principles. Through this course, you can gradually learn the basic mathematics required for artificial intelligence.

This course is designed to help those who want to deeply organize deep learning and grasp the big picture by focusing on theory and context rather than hands-on practice. You can easily understand the mathematical and statistical background that forms the foundation of deep learning, and gain an intuitive interpretation from a developer's perspective of the principles behind major modern deep learning models such as AutoEncoder, GAN, Transformer, and AlphaGo.

Anyone who likes math, raise your hand! Anyone who wants to learn probability and statistics, raise your hand!

Understand machine learning concepts, AI learning principles, and mathematical principles for model implementation to fully utilize deep learning!

This course will help you build your knowledge of advanced integration of multivariable functions.

Math-based thinking skills that develop the ability to think for yourself! Are you working overtime today? If so, I hope that through this course, you can improve your mathematical thinking skills and perform your work efficiently.

You can understand the theoretical operation principle of the Kalman Filter through easy examples.

This lecture is designed to provide a foundation in middle and high school mathematics for adults who gave up on math during their school years but are now looking to tackle engineering mathematics.

Attention to those who want to study stocks! But, you are studying stocks without knowing financial engineering? How about learning how to make money properly through financial engineering from the basics?

Theory, numerical approximations, intuition, and visualization in integral calculus. Enhance your math-coding skills.

Dynamic Programming That's Untouchable, From Math to Key Elements to Look for in Problems, Complete Summary from Basics to Practice

This course covers university-level first-year calculus. We focus intensively on single-variable function differentiation and learn various differentiation methods and formulas. As practical applications of differentiation, we select and study cases such as linear approximation, function increase and decrease, and optimization problems.

For those who are interested in game development and know that math is important, but don't know what math to study, I've prepared a lecture that provides a general explanation. I want to talk about the various maths used in the game production process.

How should we integrate the results of different diagnostic methods when they are different? Are there any diagnostic methods that are unnecessary among the various diagnostic methods? We will provide answers to these questions.

Develop a deep understanding and intuition for calculus. Solve problems and implement algorithms by hand and in Python.

The core of all AI/deep learning is ultimately optimization. Of course, optimization theory is not only needed in AI/deep learning. Computer vision, robotics & control systems, financial engineering & quant, data science, signal processing... Probably no matter which field you study, optimization theory is one of the topics you will inevitably encounter when you go deeper. This lecture systematically covers everything from basic mathematical theory to in-depth content. I believe it is by far the best optimization theory lecture offered in Korea.

If calculus is too difficult? From the basics, step by step! Covers university-level calculus.

Learn why Propensity Score Matching analysis is so popular and what its advantages are. Also, use it to easily create tables and graphs that can be used immediately when submitting a paper.

Were you a math-phobe during your school days? It's said that math is important in AI, but do you feel lost on how to approach it? The reason math is important in AI is because math is used in the computational processes of AI (Machine Learning and Deep Learning). For easy explanations of differentiation, linear algebra, and probability and statistics to understand AI, it is structured with simple explanations using graphs (coordinates) rather than mathematical derivations.