6 avr. 2019
A bit easy (python wise) but maybe that's just a reflection of personal experience / practice. The contest is easy to digest (week to week) and the intuitions are well thought of in their explanation.
26 nov. 2017
Fantastic introduction to deep NNs starting from the shallow case of logistic regression and generalizing across multiple layers. The material is very well structured and Dr. Ng is an amazing teacher.
par Pantelis D•
19 déc. 2020
An excellent followup to the ML course of the same professor (Andrew Ng), similar short, on point and clear videos that serve as an introduction to Deep Neural Networks.
In this course the programming assignments are coded and submitted in the browser using Jupyter notebooks, the coding language used is python and for the math the python library "numpy".
It is worth mentioning that some interviews with influential people on the field of DL are included and make the student fall in love with DL even more. Excited to see what's next in this specialization.
par Ged R•
7 sept. 2017
I completed the original ML course earlier this year which gave the fundamentals of the practice. What I got out of this course was a reinforcement of the practices and ways of collecting my thoughts. There was enough difference in the approach and especially in the back prop areas to help clarify the understanding from what was a bit of magic, to a clear and more structured set of calculations. The platform of using the notebook is very solid, and of course there is the usual outstanding support from the community with respect to answering questions
par Chris M•
12 août 2019
Andrew NG's approach is one of its kind. Previously, I had taken several courses with other reputable online providers, and also did a lot of reading in tandem. What amazed me about Andrew's approach was the fact that crucial concepts were explained in much detail, one-by-one; this helped me complete the overall puzzle and/or fill in any missing links. I'm not sure if I could've followed the course without any previous experience, but if you're familiar with Python, NumPy and basic ML concepts, then this course will help you understand DL a lot better.
par Basil A•
22 août 2017
I think this course is very accessible, and gives you enough know how to hit the ground running. My only caution is that there is a bit of hand-holding involved (because of the limited background they assume), and that if you want a more rigorous foundation, you'll have to supplement this course with other materials. This doesn't detract from the quality of the course though, rather, it's amazing how much you can do with Deep Learning without fully understanding all of the finer details, and this is a good place to springboard into more advanced study.
par Sebastian S•
19 juin 2021
This is an excellent introductory course to Machine Learning and Neural Networks in particular. I've always wanted to know the nitty gritty details of how code of neural networks is written instead of using already developed third party packages. Thumbs up to the instructor and the entire team! My only comment is that the course suddenly changed when I was on week 4 and I lost all of my previous work for weeks 1-3. I wasn't notified of this change and I had to redo all this work. I got refunded for a month, but the redo work still took a lot of time.
par Eduard L•
31 oct. 2018
After a full course of Machine Learning, of course, this one is rather weak. The feeling that all 4 weeks we are talking about the same thing. This is probably done for those who are not at all in the subject. I see this course as an introduction to the specialization. I hope the continuation will be stronger. It's great that practical work is done in Jupiter on Python. Program exercises are easy, but it takes a lot of time to figure them out if we don't know Python very well. This is not a plus or a minus, just a statement of fact. Thank you Andrew!
par Bernard O•
21 oct. 2018
This was an amazing course for me. I've always wanted to get to the bottom of deep learning fundamentals and this course did not disappoint. It walks me through the basics to the more deeper concepts in incremental steps without overwhelming me with too much derivatives (but just enough to carry the point across). Just the right mix of theory and practice. Highly recommended as a starting point for deep learning, or if you're like me, developing more intuition towards the practice that I am already doing. Fills in the gaps in my understanding nicely.
par Steven K•
8 juil. 2018
A very nice introduction to deep learning. Covers the basics and builds up slowly. There is some prerequisite knowledge of Python programming and calculus to have success with the course. Professor Ng's explanation of the topic is focused on practical applications, and builds on years of experience gained in academia and industry. The exercises are focused on mastering core concepts. The notation takes a little bit of time to get accustomed to, but you begin to understand why the notation is the way it is. Very good course; I definitely recommend it.
par Romina s•
8 janv. 2018
A really good intuition and introduction to neural network and deep learning. What I enjoyed the most was the fact that we needed to implement the learning algorithm step by step through the guided programming assignments as opposed to calling an in built function in libraries ( such as tensorflow etc). I felt the programming exercises were quite very successful in an attempt to draw and maintain the learner focus on the algorithm itself as opposed to other programming aspects, which can be learnt elsewhere/improved elsewhere. Great course. Thank you
27 juin 2020
I like the practical focus of this course, it allows you to build the fundamental parts of simple tools that are gratifying for us beginners.
The instructor focuses on making sure he teaches only the core concepts and sometimes he does only explain some concepts at a very surface level, but I see this as more of a feature than a bug. Linear algebra and calculus concepts that are only briefly discussed in this course, deserve their own class or course; I like that is up to the student to decide whether to deeply research these subjects on his/her own.
par Ankur G•
12 nov. 2017
This course makes you implement your own neural network without using Tensorflow or Torch. As a result, the student gets to learn what neural networks are implemented internally instead of only learning how to use a particular software package. The course is full of small, practical, and highly useful information such as why we use a cross-entropy loss instead of sum of squared errors loss and why do we need to initialize parameters using not-too-large random weights. This information is very useful in implementing NNs at work or for job interviews.
par Wei L•
17 août 2017
It's a very good course. It illustrates the idea of neural network and deep learning in an intuitive way. I think this time I fully understand the idea and details behind them. Also, the python programming is very friendly. I have used R for years but not so familiar with python. However, folloing the instructions I can do the coding very efficiently. I think i just spent less than 1 week on this course but get 100% score on it. So it's not so challening compared to Machine Learning and PGM. I think PGM is the most difficult one among these courses.
par Dr. H K G•
24 mai 2020
Dear Prof. Andrew,
It is my pleasure to express gratitude and thankfulness to you and your team.
I am grateful to have you as a mentor in learning AI for everyone, neural networks and deep learning. It was a great journey with you in this learning process. Lectures and assignments made me realize the importance of the ANN and other advance tools in real world applications. The mathematical content behind neural network theory and programming assignments encouraged me to pursue this area in future.
Thank you once again.
Dr.Hari Krishna Gaddam, India
par Nicholas K•
7 nov. 2019
Overall, an excellent course! The material is taught very well. The programming assignments were enjoyable and fairly straightforward. The Jupyter programming notebooks were really cool and fun to work with.
The only criticism I have is that week 1 material was extremely easy, easily doable within a day. Week 2, on the other hand, was quite difficult. I think it was the most difficult week overall because it introduced a huge amount of new concepts and math. After I had a good understanding of week 2 material, the rest of the course was not so bad.
par Rohan S•
24 févr. 2019
This course is a masterpiece. Excellent for beginners and for those who want to refresh their memory. Andrew Ng's way of teaching neural networks with the simplicity of matrix multiplication deserves a standing ovation.
Course Content - 5/5; The material is extremely well structured.
Simplicity - 4/5; though the course requires basic calculus, it shouldn't be a problem
Assignments - 5/5; they were challenging, but it made sure that you grasp the concept completely.
Teaching - 5/5 - Excellent delivery by the master supplemented with easy explanations.
par kristof T•
7 avr. 2018
Très bonne introduction sur le Deep learning. L’instructeur nous explique les fonctions de base très clairement. C'est ensuite suivi d'une forme de TD ou l'on peut implémenter ces fonctions en python et s'en servir sur des cas concrets.
On ressort en ayant compris.
This is a very good introduction to deep learning. The instructor explains very clearly all the intuitions and the basic fonction of neural network. Then you'll have an assignement where you implement thoose function in python and use them on a real example.
par Aditya V B•
5 mai 2020
A very beautiful course that introduces us to neural networks and helps gain insight on how neural networks work. One who doesn't know linear Algebra and/or Calculus can also understand the concepts. Programming assignments were good, helped visualize the neural network learning.
The derivations of gradients using Calculus should be proved/solved in an optional video, as it may help people with Calculus background understand the material in depth.
Overall, a very nice course to introduce Neural Networks and Deep Learning, would recommend 10/10.
par Sarmad A•
26 sept. 2018
Very well made. Andrew Ng taught all the core concepts of neural networks very well. Before taking this course, I've watched videos on workings of neural networks. Forward propagation and back propagation always seemed a bit hard to me but Andrew made these concepts very simplified and made me to understand them thoroughly. Extremely satisfied by this course, looking forward to course 2. I would recommend this course to anyone, no prior knowledge of machine learning is required. If you have any interest in this field, I would say just dive in.
par harm l•
23 août 2017
Great introduction in neural networks / deep learning. Using Python learning environment is easier than using R which causes me to spend lots of time in installing the right packages in the right versions. Drawback is that i don't have the programming environment ready after finishing this course. It leaves me with knowledge but i have to rebuild the models in a tool i can afford leaving me with lots of overhead things to learn and implement. Overall, good focus on the matter and it's a great surprise to have these results in such an easy way.
par Thejus H R•
9 mai 2020
Andrew NG really knows his stuff, 10/10 would recommend in a heartbeat! Course is obviously complex, but well worth the time and energy you put into it.
If there is one suggestion that I could give, it is that the grading for the assignments be improved. The grader, in my experience, only gave me either full for each component or a zero. Any change I made in learning rate, etc, did not give me any partial marks.
Other than that, I cannot thank the team behind this, clearly a lot of work went into this seemingly labor of love! Thank you so much.
par Ferenc F P•
8 mars 2018
Prof. Andrew Ng provides in this course a comprehensive step-by-step instruction to build up your own deep feed-forward neural network (DNN) with backpropagation using only the numpy (library for array manipulations). His approach is from bottom to top starting explaining very basic concepts as building blocks. After those bricks are ready you can easily build your own DNN. It is a great course for beginners wanting to understand how a DNN works. Notebook assignments are moderately hard for a beginner and easy for a programmer with practice.
par Volodymyr B•
21 juil. 2018
Great course! A lot of useful information; definitely worth it, even after taking the into course. I do have two problems:
1) I wish the programming assignments did not help you THAT much. The assignments pretty much tell you what to write. As a contrast, I think that the assignments in the intro course were much more challenging.
2) Although I was able to do the derivation myself, I wish there was optional videos to show the derivation of back-propagation, as I think it is a valuable piece of information for full comprehension of the process.
par Milo C•
5 sept. 2017
I have pass this class.
Except test case of L_model_backward is not match to the teacher, everything is very good.
For the learning strategy, I also have some suggestion for new learner.
If you don't has any experience about machine learning, then Machine Learning class in Coursera by Andrew Ng is good for basic background knowledge. It can help you to quickly understand in simple way. so you can quickly understand the course of Neural Networks and Deep Learning.
Thanks Andrew Ng make everything become simple and good to learn :) Thank you
7 janv. 2019
This Deep Learning course on coursera platform just meets my needs. The instructor of this course is Professor Andrew Ng, who has many years of experience in this field. His Instructional videos and textual materials can help me understand the essence of the theory of deep learning. In addition, after-class quizzes and programming assignments can also greatly increase our practical skills. Therefore I believe this Deep Learning course can help me to possess the basic ability to work in the field of artificial intelligence and deep learning.
par Ryan S•
4 déc. 2017
Very basic concepts are taught, but the material is presented clearly and relatively concisely. The concepts are very accessible and some depth on the mathematics and theory is provided, although not as much as you would get in a graduate level college class. The programming assignments are very good, balancing first-principles implementation with a focus on implementing the most important concepts rather than writing boiler-plate code. This is a good introduction for practitioners and is easily covered in much less time than that allotted.