Complete mastery of deep learning theory + PyTorch practice

I really appreciate the thorough and systematic learning from the basic theory of deep learning to advanced practice. In particular, the practice files provided through Colab made it easy to follow the lectures one by one. Thank you for the great lecture!

This is my first time studying deep learning and using formulas to study the theoretical part. It was more difficult than I thought, so it took time to study and review, but it was fun and rewarding to understand it one by one and move on. I think I will keep this lecture and review it whenever I need to. Thank you for the great lecture!

This is a lecture that even a beginner who knows nothing about deep learning can follow. I think it would be easier to follow if you have some basic knowledge of Python. The lectures are broken up into short bursts, and since you can check the contents through the curriculum, it was helpful to be able to study while understanding the context in which the lectures were being conducted. There were times when I wanted to give up because the math content that came up here and there was difficult, but it was helpful because it was explained in a way that I could understand well. I bought a lot of books to study deep learning, but I gave up studying on my own several times, so I listened to the lecture for the first time. It was a million times more fun and easier to understand than reading a book on my own, so it was really good!! Thank you for the great lecture :)

There are many good lectures on Infraon, but I can tell you that this is a lecture with excellent content that is definitely one of the best among lectures related to deep learning. I think it will be more helpful if you listen to it with a general understanding of the big concepts of deep learning. The important concepts for practical application were explained very clearly, and the theory part was more impressive than I expected, so learning PyTorch felt like a bonus. ㅎㅎ I started deep learning with TensorFlow, so I paid to learn PyTorch, but I gained a lot of theoretical concepts about techniques that I was curious about during my work, and I am also increasing my understanding of PyTorch coding methods by following the practice. In conclusion, this is a lecture and content that is definitely worth the 300,000 won! Thank you for providing such a great lecture ^^

Although this lecture is for beginners, it seems to be a good lecture for reviewing the main concepts for practitioners in their second or third year. Among the numerous theories and papers on deep learning, the important core concepts are organized in a well-organized manner, and the lectures are separated by subconcept, making it easy to find the content you need. It was also helpful for my work because it explained the concepts as well as the implementation in an easy-to-understand manner. I wish I had taken this lecture when I was a college student, but I regret why I only took this lecture now. I recommend it to those who want to grasp both concepts and implementation.

I am currently working as a backend developer. At first, I hesitated to take the course, but after taking it, I think I made a good choice. I have always been interested in ML engineers, so I took the course. Of course, my recent interest in artificial intelligence was also a decisive factor in taking the course. First of all, the vague concepts I learned in college were explained in an easy way, so I was able to understand them clearly. In particular, the formulas were explained easily during the theory lecture, so I was able to understand the formulas well. In particular, it seems to be the perfect course for people like me who only have a basic, superficial understanding of ML. For reference, I had a hard time with my thesis when I was in graduate school. If this course had been available at that time, it would have been very helpful. If you are interested in graduate school artificial intelligence or need conceptual content when writing a graduate school thesis, I think it would be very helpful to listen to it at least once.

This course covers a wide range of topics from the basics to advanced topics of deep learning, and I liked the hands-on approach using PyTorch. It covered a variety of topics, including setting up the PyTorch environment, basic concepts of deep learning, loss functions, gradient descent, activation functions, optimization, regularization, learning rate schedulers, initialization, standardization, CNNs (Convolutional Neural Networks), RNNs (Recurrent Neural Networks), and the latest topics such as Attention and Transformers. The course is designed to be easily accessible to beginners, and each section consists of various exercises along with theoretical explanations, so I especially liked the fact that learners can experience the principles of deep learning by writing code themselves. In particular, it is recommended not only for those who are new to the field of deep learning, but also for those who want to refresh their basic knowledge, as it allows them to learn step-by-step from basic concepts that can be applied immediately in practice to advanced topics. Each topic is covered in depth with ample practice and examples, which I believe will allow learners to comprehensively understand the various aspects of deep learning and develop the ability to apply them to solving real-world problems. The systematic organization of the lectures and the practice-oriented approach provide learners with the practical experience necessary to actually utilize deep learning technology, and I highly recommend this course to anyone interested in the field of deep learning.

This lecture can be helpful for both those who are new to the field of deep learning and those who want to review important concepts. For those who are new to the field, the lecture is well organized from the bottom up so that they can follow the flow by following the table of contents, and for those who are already in the field, it seems that they can quickly review the concepts that I was weak in. The lecture table of contents and internal structure seem to have captured the essential elements without unnecessary details. The structure and content are very clean. In addition, the lecture is well organized with content that would be of interest to those in the field. For example, - So what kind of logic is used for the internal operation? - So how do you implement it? I felt that these two were well differentiated. In fact, it is well-incorporated with empirical content that can be learned from the perspective of work performance, not just from the perspective of an instructor.