
Deep Learning with Excel
hjk1000
Let's visually learn the principles of deep learning using Excel.
입문
Excel, Deep Learning(DL), VBA
Why this course is special: Key Advantages • Intuitive Visualization: Directly observe algorithm operations in real-time with Pygame 2D simulations • Practical Implementation Experience: Go beyond theory and internalize autonomous driving algorithms by coding directly • Master Core Algorithms: Focused learning of essential algorithms such as Dijkstra, Pure Pursuit, ICP, etc. • Step-by-step Advanced Learning: Systematic difficulty progression from basics to SLAM • Lidar-based SLAM: Practical map building and localization in unknown environments
SLAM (Simultaneous Localization and Mapping)
ICP (Iterative Closest Point)
Dijkstra Algorithm (Dijkstra Algorithm)
Pure Pursuit Algorithm
Ackermann Steering Model (Ackermann Steering Model)
Autonomous Driving, Now Let's Understand the Whole Thing Easily!
In recent years, autonomous driving technology has made remarkable progress and has become an important part of our lives. However, when trying to jump into this exciting field, the educational materials that we encounter are disappointing. When we look at autonomous driving lectures on the market, we find that they are largely divided into three types.
The first is a lecture that is too basic . It only conveys superficial information such as the concept and history of autonomous driving, and does not provide a deep understanding of how the actual system works. It is an interesting lecture, but it does not quench the thirst.
The second is a lecture that focuses only on AI, especially deep learning . For example, there were many cases where they only focused on how to recognize lanes and steer using deep learning. Of course, deep learning is one of the core technologies of autonomous driving, but it is only one part of the autonomous driving system. The basic engineering principles that are not AI, such as creating maps, planning paths, and controlling vehicles, are much more important and widely applied. These lectures did not allow me to see the whole picture of autonomous driving, and it was like not seeing the forest for the trees.
The third is a very difficult lecture . It suddenly pours out complex mathematical formulas and theories, or only covers concepts that are far from actual implementation, creating a barrier that is difficult for beginners to approach easily. Most of the lectures are full of the will to learn, but they are frustrating from the beginning.
In the midst of this regret, I asked myself, "Isn't there a lecture that can easily and intuitively understand the entire autonomous driving?" And after much thought and by mobilizing all of my knowledge, I created this lecture myself.
This course is designed to overcome the limitations of existing courses and to enable you to understand and implement all the core elements of an autonomous driving system from start to finish .
Using 2D simulation based on Pygame, you can intuitively understand the operation of complex autonomous driving algorithms by directly observing them . It clearly shows how theoretical concepts are implemented in each line of code and simulation screen.
It starts with path planning and following on a known map . The map is divided into a grid and the shortest path is found using the Dijkstra algorithm. Then, the vehicle is controlled based on the Ackermann steering model and the Pure Pursuit algorithm is used to accurately follow the generated path. This is the most basic 'thinking and moving' process of autonomous driving.
Furthermore, it expands to autonomous driving in an unknown environment where the map is unknown . It simulates the Lidar sensor and uses this Lidar data to build a map of the surroundings in real time. At the same time, it implements SLAM (Simultaneous Localization and Mapping) that estimates the exact location of the vehicle through the ICP (Iterative Closest Point) algorithm. It regenerates the path every time the map is updated, allowing the vehicle to find its way on its own even in unfamiliar terrain.
This course does not simply blindly follow AI technology, but covers all four core pillars of autonomous driving : Mapping, Localization, Path Planning, and Control . Through this course, you will draw the 'big picture' of autonomous driving and clearly understand how each element is organically connected and works.
Don't be frustrated by the complexity of autonomous driving anymore. This course will provide you with a solid foundation for learning the core principles of autonomous driving in an easy and fun way, and furthermore, for creating your own autonomous driving system. Let's go into the exciting world of autonomous driving together!
Recognizes an unknown environment with LIDAR, creates the shortest path, and follows the created path
Who is this course right for?
Newcomer to autonomous driving
Those wanting to learn autonomous driving's core principles beyond AI/Deep Learning
Those desiring deep understanding through practice.
Need to know before starting?
Python Programming Basics
High school level basic mathematics + matrix operations
Computer Science Fundamentals (Optional)
1,441
Learners
32
Reviews
7
Answers
4.7
Rating
9
Courses
안녕하세요
비전공자로 딥러닝을 열심히 공부하는 직장인입니다.
공부하면서 느낀 점들을 여러분들과 함께 공유하고 싶습니다
감사합니다.
All
9 lectures ∙ (3hr 10min)
Course Materials:
$17.60
Check out other courses by the instructor!
Explore other courses in the same field!