Introduction to Deep Learning Series 📖

Hello! Welcome to the world of Deep Learning, created by [Engineering Student] :)
Deep Learning is a relatively new discipline, so there is no systematic curriculum yet.

While there are certainly numerous educational resources on deep learning , when conducting actual research and development, you'll need to go far beyond these resources and engage in self-directed learning. This is because most lectures tend to offer overviews of various concepts to cover the entirety of deep learning.

Let's take an example. Typically, lectures cover " Residual Networks" for a few dozen minutes at the shortest, or an hour at the longest. What would happen if you took this course and actually worked on a project?
We research and develop through countless additional resources and trial and error.
How great would it be if there was a lecture that focused solely on Residual Networks?

[Engineering Student]'s Deep Learning Series was created for these people 🙉

As shown above, the world of Deep Learning encompasses countries both large and small. Through this Deep Learning Series, you can travel to any country you desire. You can stay in one country for a long time to gain a deeper understanding of it, or you can travel to several countries more casually. Over time, I expect you to become experts in all of these countries!

Introduction to the Course 😉

In the world of deep learning, understanding convolutional neural networks (CNNs) is essential. The most reliable way to learn CNNs is to understand the ideas behind successful networks, implement them, and master each one .

This course is about entering the country of Convolutional Neural Networks. Because you'll need to go through this entry process to explore cities like LeNet, AlexNet, and ResNet , it lays the foundation for understanding the various CNNs covered in the Deep Learning Series .

Let's Go 🛫

Upon entering the country, you will receive the following travel instructions:

Related Lecture 👍

This course is best taken in conjunction with the TensorFlow User Manual. ➡ Link