Artificial Intelligence II - Neural Networks in Java (Udemy.com)

I've attended the other Udemy course of the author: "Artificial Intelligence I: Optimization and Games in Java" which was good. But this one is much better as I can see a huge progress in using English or presenting skills. Also, the material covered here is more advanced but taught in a nice and understandable way.
I do not recommend this course for students who are very new to the concept of the artificial intelligence as quite complex topics are mentioned. If you are not familiar with AI, then please try "Artificial Intelligence I: Optimization and Games in Java" first.

Easy to understand when you can see the implementation examples

It was very basic and didn't get into the details or the math behind the backpropagation. Good for those who want to get an introduction to neural networks.

Gave me a good understanding of how learning happens in the system. Unfortunately some of the videos are blurry, but hope this will get sorted out.

Explained a complex topic with easily understandable terms.

So far so good.

Very clear, understandable. Teacher speaks a bit slow for my taste, so I had to adjust speed ratio to 1.25.

This was a good course. Looking forward to taking others.

Good match.

Los temas tratados clarifican muy bien los conceptos sobre Redes Neurales.

Hi, in this review we are going to talk about the second course in Artificial Intelligence on Neural Networks. Once again Holczer has a simple format that each of his videos follows. I like the balance of theory and application that Holczer has shown in both of these Machine Learning courses. The concepts are explained well, and easy to follow. While many other courses seem to be theory and mathematics heavy. This particular course has one optional lecture that has a need for Calculus. Holczer shows how we get to a simplified equation that is then used in other lectures. The simple Back Propagation Neural Network code, that was developed in this course, can be used over and over for a variety of use cases and turns out to be quite fine. I found that reimplementing the exercises using a tool like DL4J helped to cement a few concepts. I thought the section on installing Paint.Net was unnecessary and was specific to Windows (provide alternatives for Linux and Mac). Thanks for reading! :)

The basic concepts of NN were explained in detail. The lecture can cover the necessary materials, maintain consistently and connect smoothly. The code is simple and easy to understand.
Just three issues that I am confused. (1) Hopfield NN is almost 50 years, is it necessary to explain this sym NN using almost one third of the course? (2) I am new in AI and NN. The examples in this course are Logical operations and backprogation. As mentioned in the mid of lecture, it seems that a stock market example will be included. But it was never discussed. More interesting example would be better. (3) It would be nice to have some exercises or programming questions during each section for us to practice