This course provides a good overview of the optimalization techniques for neural networks. It refers to both the basics by providing an explanation of moving averages, and the advanced by providing references to academic literature. Finally, it provides the rules of thumb that a practitioner needs when iterating models.

The way these core concepts are covered making it super simple and easy to understand for anyone beginning to learn deep learning concepts. Also, the programming exercises that are curated for each concept that is being covered in the video lectures really gives you a practical exposure on the theory taught in classes.

The course part is overall good.

The last assignment can be improved in two key ways:

The comment # Z3 = np.dot(W3,Z2) + b3 should be # Z3 = np.dot(W3,A2) + b3 - figured this out by myself without help from forums. :)

Also, the Adam optimization is not very apparent in the instructions - searched in the forums for issues.

I completed the entire specialization and having nothing but good things to say. Highly recommend it! Lectures are engaging, and Andrew does a fantastic job explaining some very complex topics. Programming assignments are challenging in a good way. You’ll really feel like you’ve learned a lot by the time you’re done.

Another wonderful course of this amazing specialization. I could say a lot of things, maybe even pages on how Professor Andrew it's the right person to teach you about Deep Learning but I'll shorten in this review and recommend the whole specialization for you! It's worthy and there's a lot of knowledge to be shared!

In my deep learning classes in academia, hyperparameter tuning was always "hand-waved" away - my questions were always deflected, or put off. This class answered every one of my questions, and made me more confident I'd be able to implement a DL system in industry, and be satisfied with the results. Very good course!

This course will cover everything you need regarding your neural network performance. I always had questions on why and when you use Adam, SGD, etc. and after this course, I have a much better understanding of how to choose hyperparameters and optimization methods. I highly recommend this course to ML practitioners.

I am working through the DL specialisation. Consistently good teaching style and the programming assignments are suitably pitched for getting the learner to pick up methods quickly e.g. Tensorflow syntax for self-application later. Good course and looking forward to the next in the series. Well done Andrew and team.

word is not sufficient signup and experience it. For a deep learning beginner who already have math background can easily understand concept behind it but for implementation you need to refer extra materials on internet and book too. Andrew Ng explain only concept and recipe but for practice you will struggle hard.

Great course! Help understand the mathematics and intuition behind hyperparameters and regularization methods. I feel the material is well-prepared. However, the last lab is quite confusing because I think we are not prepared enough about tensorflow fundamental throughout the course to really apply it in practice

This course is continuation and a requirement of the first course. Really like the learning style of how first course and the first 2 weeks of the second course taught neural networks by doing all the math and calculations manually and finally introduced Tensorflow with parallels of what was taught in the class.

This is another excellent course in this specialization. I enjoyed the programming assignments. The instructions, tips made Tensor flow coding section to be easy . However, few blocks consumed more than few hours, due to placeholders. logic and the TF documentation is overwhelming. I am proceeding to next course.

This course is harder than the previous one. It teaches more details of tuning parameters and optimization in deep learning. In the end it also teaches tensorflow which is really helpful. It's like a programming course, nerally all the commands have been already provided, so it's not hard to get the code correct.

As usual, Andrew is a great instructor. He taught very complex concepts in very simple language and used notations that were easy to understand and were consistent throughout the length of the course. WOULD DEFINITELY RECOMMEND. I am hoping to complete the specialization in less than a month. 2 down, 3 to go!!!

It is really good and teach me the basic understanding of DeepLearning back propagation and gradients optimization like Momentum, RMPS, Adam finally I learn how to use Tensorflow to train my model.

But there are some mistakes in the assignments and also in the grade so that it costs me a lot of time but useless.

It was a good course on understanding various hyper-parameters, some regularization method, optimization of algorithms, various gradients and gradient checking, batch - mini batch, exponentially weighted average , some tuning algorithms and finally a small introduction to deep learning frameworks. RECOMMENDED!

The course content was excellent. The only issue is that there were some glitches with the grading of the second week programming assignment, in that I could obtain the expected output, but with repeated submissions, there would be (different) sections which could not be graded due to unnamed technical issues.

Amazing course by Andrew sir really helps understanding the mechanism of optimizing a machine learning model , the practices he taught will help me in speeding a better model with better accuracy .

Thanks to Coursera and Andrew sir for sharing the knowledge and experience of various legends of machine learning

5/5.Thank you sir for helping me in my career.I recommend everyone to go through this course if you really want to learn detail about hyper parameter tuning , optimizers and regularization used to make neural network better. It helps to open black box of Neural network and know in detail about how all works.

Excellent content and very well explained. Thanks for this amazing course.

The course cover the building blocks of a Neural network. Andrew (and his team) did a great job by organizing the content in an evolving way in which you have the chance to build the knowledge from each piece of a (deep) Neural Network.

Practical programming lessons, and well-paced enjoyable lectures.

Comments:

Move tutorials on TensorFlow to Course 3, which was the most obscure part of the course. TensorFlow isn't as intuitive as other numerical toolboxes, so spending more time on the foundations of TensorFlow might reduce the learning curve.

Intuitive, in-depth (while not losing the big picture), engaging and well structured, with amazing assignments to revise and solidify everything you learn in the videos. These courses are awesome! Just one suggestion: It might have been nice to have more intuitions on BatchNorm in the assignments. Thank you!

A wonderful AI course! In most Ai courses we could only learn some specific algorithms. In this course, however, we could learn beyond AI itself. There are many practical AI skills in this course like hyperparameter tuning, regularization method and optimization strategies! I benefit a lot from this course!

It covers very good tips and tricks to build and enhance deep learning model.

Andrew is the best teacher for ML and Deep Learning, he covers all theory and practice simultaneously.

In this course you can understand all mathematical intuitions and implementation of neural network from scratch by your own codes.

Another great class taught by the incredible Prof. Ng! I have to admit there were time I felt a bit overwhelmed but by the time the course came to an end, I felt like everything "clicked". Very much looking forward to the next course and can't wait to dive deeper in ML frameworks. TensorFlow, here I come :D