Very detailed and consistent course, very good for complete beginners but also provides insights regarding the math foundation. Very informative and easy to learn.

The method of teaching step by step and explaining everything is just clear and perfect. The assignments are also of good level and test your knowledge and aptitude.

Very useful course even if you have some previous knowledge on machine learning. This course use a well designed notation to make the complicated calculation simple.

Excellent introduction to Deep Neural Networks! You do not need a background in Machine learning if you basic undergraduate knowledge in Calculus and Linear Algebra.

Love it. Great foundations course for executives who want to be able to better interact with its data scientists and start to explore uses of ML in their businesses.

great introduction to neural networks!! i appreciated the helper modules in the programming assignments to get the point across, didn't have to do much heavy lifting

Perfect course for a beginner in Deep Learning.

One who already has hands-on in DL might find it basic. Still, I would recommend as it helps in refreshing DL basics.

Great intro level course to deep learning. Concepts are explained well with ample additional reading material. Congrats to Andrew and the team, the quality is great.

I really love how Professor Andrew Ng designed this course. He explained every single details very carefully, so it is very easy to follow and understand. Thank you!

it is really a good course to learn about neural networks. anyone with basic knowledge of maths, can easily understand the concept of neural networks and master it.

This course is really good for AI newbie like me. You can learn and practice regularly, so I think your skill is gradually improved. Tks this course for helping me.

Great course. Explanations are very elaborate and you can see they really try to explain even when this is something not so easy to understand. I really liked that.

Excelente curso!

Se abordan los contenidos en profundidad y al mismo tiempo de forma práctica, permitiendo a los estudiantes aplicar los conceptos desde el inicio.

I really like the comprehensiveness the course was going through. Although sometimes I felt a little too carried by the code I had to write in each GRADED Function.

Incredibly explained by Prof. Ng, and a great help from mentors to understand NN. I am really grateful to the team and Coursera for making learning so easy and Fun.

A great introduction to neural networks. You don't need to know much calculus going in but any pre-existing calculus knowledge will only help you get more out of it

I think this course is really qualified and instructive.

An extremely good course for anyone interested in Deep Learning.

Thanks to Adrew NG and DeepLearning.AI team.

It was very interesting and full of knownledge course. I especially want to thank Mr Andrew NG for his very clear explanations and instruction. Thank you very much.

Es un excelente curso de introducción al tema. Andrew sabe con mucha precisión lo que se requiere para empezar y la manera evolutiva de presentarlo. Muchas gracias.

Excellent course. I am delighted that I got to build my first neural network. I really love the content taught. Working out the calculus part is thoroughly worth it

I am from INDIA.I have never seen such a great mentor who always makes a hard topic so easy as if its nothing.Thanks to Andrew NG and his team for this great course

Amazing course. As expected from Andrew and his team. The course provides a great balance between theory and practice, and the assignments are beautifully designed.

At the beginning I knew nothing about neural networks. With the systematic and proper lectures I got a clear understanding about neural networks and deep learning.

Excellent balance between the fundamental math/theory of neural networks and practical application. Jupyter notebooks make completing the exercises very convenient.

Thanks to Andrew Ng and staff for helping me to build intuition on what deep learning is and inherent methods like feed forward, backward prop and gradient descent.