I'm a beginner in ML so i don't know much to say but this course teaches what it says it will do. In the middle of the course you may be having lot of questions about how it all fits together, but they almost always get clarified in the end.

A bit hard to follow but worth the time spent as this course helps to build the intuitions behind some of the most famous optimization algorithms and tuning methods by making the students work through them using only basic python and numpy.

Very practical course for implementing deep neural networks from scratch. The ideas of hyper-parameter tuning, regularization and optimization are very refreshing even for experienced deep learning engineers. Learned a lot from this course.

Continuing the trend of magnificent course content, Dr. Andrew Ng walks us through some exceptional practical advice in implementing DL algorithms, detailing the concepts and the best-practices, and mentioning the pitfalls. Simple awesome!

It's a very good course for those willing to dig into the nitpicking of it. If you're really serious about this field, or if you're going to use neural networks often in your job, these lectures (and notebooks) can save you a lot of time.

This is an excellent class for understanding how to tune neural networks. I guess this will continue to be a valuable skill set until we have neural networks that can figure out optimal parameters to design and tune other neural networks.

I've worked with deep neural networks before for a while, but this course gave me a lot of new ideas, especially different tips and tricks on fine-tuning hyperparameters and speeding up the training of a deep neural net. Highly recommend!

This part is one of the most important to working with NN or DL nets. The instructor has achieved to teach a not so easy topic in an awesome manner so everyone is able to tune his networks as a professional. Can't wait for the next part.

I this course I learned how to improve Deep Neural Networks by applying different methods that help to speed up the convergence and to reduce overfitting. Also, now I have some basic knowledge about using TensorFlow. Thank you very much!

pretty good course all in all !, I would say considering the difficulty of this topics, the instructor has done a great job in transmitting the relevant parts that one needs to remember and also in justifying why things are as they are.

Very well structured class as a follow-up to the first one. Heavy on information but this is a good thing. As someone who isn't pro at Python, the development part was much smoother since programming wise it is similar to the first one.

En línea con los anteriores. Muy teórico pero perfecto para entender los entresijos del funcionamiento de los algoritmos. Si acaso echo en falta algo más de tensorflow pero supongo que se verá en el resto de cursos de la especializacion

I really like the practical aspects of the course where although there is a focus on teaching the fundamentals, there is also a good focus on teaching the latest frameworks to apply the knowledge of the learnt concepts more efficiently.

Excellent practical advice on running NNs. The lectures teach the subject matter in a lucid and intuitive way. The course ends with a TemperFlow exercise that shows how to implement NNs at a higher level than peviously shown with numpy.

Great material. Short, precise videos.

It would be great if you propose projects to work on outside the course, in order to learn more about the topics. Just like ideas where we could apply what we have learned and a seed to build upon.

Loved the programming assignments. After learning Tensor flow in this course, I learnt about Keras on my own. It made model building very easy, but without understanding the basics, going straight to Keras would make a person dangerous.

Again, the course was great. Covering a large spectrum of deep neural net adaptations and configurations of its hyperparameters give me a better understanding and tips with how to best use this deep learning technology. Congratulations!

I can't emphasize how much I enjoyed this course. The course material is clear, structured and well laid out and each concept builds on the previous with repeated emphasis on key walk away points. Can't wait to start the next course :)

This is a great course like other ones in this specialization. I learned from this course why we need regularization, how to do them exactly, what are the rules-of-thumb for setting hyperparameters, and how to find them systematically.

After learning neural network and deep learning it is important to learn improving networks.This course gives idea to improve your network.Only knowing how to build a neural net is not okay you should also know to improve the network.

Had a lot of confusions on why and how to tune hyper parameters. Got a good amount of knowledge in Mini batch, batch normalization, momentum, Adam and RMS prop. Will surely be useful when I tune hyper parameters in my future projects.

Great course. It was a little short, but covered the necessary parts of hyperparameter tuning. I also liked how the last homework was done using TensorFlow and how the courses in the specialization build upon the preceding lectures.

Teaches "what it is" and "how to do it". Clear steps, easy to follow. It would be great if you can also teach "why it is like this", or say, why is regularization valid, what is the theoretical justification behind regularization etc.

Excellently taught by Andrew Ng. While the field of Deep Learning and AI continues to evolve rapidly, Andrew maintains calm and explains the core and relevant aspects needed to succeed in this course and hopefully also in your career.

As with the first course of this specialization, Professor takes one step at a time building/ explaining things. He explains even minor details, so it very easy to understand. Also the assignments are very useful to learn the topics.