6 de abr. de 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.
29 de abr. de 2020
Amazing course, the lecturer breaks makes it very simple and quizzes, assignments were very helpful to ensure your understanding of the content. Hope for future learners you provide code model-answers
por José A V M•
26 de sep. de 2017
Amazing!! I've took part of the Udacity Deep Learning Nanodegree, but the math there was just not enough to my taste, here the thing is different, I love all the notation and the math behind. Also there are more focus in build the model step-by-step. As recommendation, I would like to include an activity to sketch the functions of the deep learning layers. For example, if I would like to build from scratch a deep learning model, what will be the functions I will need (in the assignments I could deduce them, but I would have like to have an activity related to this). Also I would like to have a little more focus in visualizing a small neural network, and write the values from the matrix to the visual representation.
por Pradeep P•
20 de nov. de 2017
Excellent course by Andrew and team. I am a big fan of andrew teaching style (since I took his ML course), no fancy screens just basic slides with great contents and explanation. My personal fav part in this course is programming assignment, this part is made very thoughtfully I think there are always some clue in the instructions and comments which one can pick to develop code to solve assignments.
For anyone planning to take this course I would suggest to refresh maths mainly topics like calculus, Linear algrbra, though Andrew explains required maths with a great ease. but still good to have maths background.
I am excited and looking forward to explore upcoming courses in deep learning series.
All the best!
por George G•
31 de may. de 2021
Machine Learning is quite demanding of Linear Algebra and Calculus but in this course, they won't be a hindrance as Andrew manages to deliver core concepts satisfactorily even without diving deep into the math behind. The course is designed to be approachable to the widest possible audience interested in Deep Learning. This results in programming exercises being pretty much "fill in the gaps" format which may come across as way too easy and they surely are. The key in my case was to try to implement the entire notebooks from scratch a week later and that's where the programming exercises shine. These are very well-crafted concise nuggets of code that shed light on abstract ideas excellently in a programming way.
por Paolo A•
12 de mar. de 2020
As Business Executive I was rather skeptic and a little worried starting this adventure "in deep" as I have not programmed for many years, but still have some notions of linear algebra for luck. My personal objective is to understand AI deep networks to propagate it inside my Firm and especially to improve quality of living, freedom, sustainability in society. I think I got the right direction!
I have been very impressed by Andrew's approach and style that make you comfortable learning these not simple matters. I wish I could have time to continue the Deep learning Specialization.
Thank you very much to Andrew , to the whole Faculty Team and to the brilliant colleagues attending this wonderful course.
por Syed M I•
23 de ago. de 2019
Mr Andrew will make you climb the mountain while holding your hand.
There were sections in which I found the subject getting a better of me, but at the end of those videos he would come up and say "Don't worry if you didn't get full sense of what's going on" or "This is one of the hardest mathematical portion in machine learning" or "Even after all these years i am sometimes not confident of my approach but the model works magically".
In the confusing sections, he almost writes down the code for you to copy-paste. He had pre-written most of the codes for us, but make us feel that we are the ones writing it, because the ultimate aim is to learn things and be confident enough to replicate the learned skills later.
por Mukesh K•
22 de ene. de 2019
First of all, thanks for offering the course on the platform. Before starting the course I had a good knowledge of machine learning and have been thinking about exploring the field of Neural Networks and Deep Learning. I could not do it in my college but the course provided me the opportunity.
The course material is very concise. Professor Andrew Ng presented very complex concepts in very easy language. The Programming Assignments are very helpful. They test and enhance both your Python Programming Skills and python code Implementation skills. While doing the Programming Assignments I was not only learning the concepts but also enjoying them. The entire course as well as the assignments are very much engaging.
por Jia D•
19 de jun. de 2020
After taking this course, I have no doubt that Andrew is one of the best instructors in deep learning! He made you feel everyone could learn deep learning and do well. The quizzes examine your understanding of the concepts with many details, and the programming assignments are very well designed - one is built on the other with an increased level of difficulties. However, they never overwhelm you if you have the patience and believe you can master them eventually. The interviews with masters in machine learning also make this course even more exciting. Highly recommended to everyone who wants to start your journey in deep learning! Excited to start the next course in this specialization! Thank you, Coursera!
por NITIN B•
20 de ene. de 2021
This Course is very helpful, especially when you want to start from scratch, it gives the basic intuitions about what actually happens and how the Deep learning works. Personally, I had a bit of experience in deep learning which I kinda learnt on my own(a few basics of keras tensorflow) before starting this course but after going through the lectures and programming exercises included in this course now I have a clear picture about what really goes in and out in a neural network. Though in this course tensorflow isn't taught but hey it's totally worth it, after taking up this course now I know how parameters are really updated in a layer and how the data in a neural network actually flows through the layers.
por Prithvi B•
26 de jul. de 2020
Andrew, Take these comments as a token of my gratitude to you. From the perspective of clearing concepts, this is the best course on machine learning. I wish I would have done this course 10 year back. I have explained the concepts understood from this course to my 13 year old son and he now has an intuition of what machine learning is all about. Recently, lot of professionals have understood the concepts from your course and they all owe to you. Keep up the good work. I hope machine learning or technology proves to be helpful to human kind and governments of developing and underdeveloped countries also use them for better governance instead of being used by billionaires to get more rich. Thanks once again.
6 de oct. de 2017
Andrew you did it again! This is the best intro theory and implementation course on Neural Networks out there. It combines enough theory (optional Calculus/Linear Algebra) and full implementation. The discussion groups are great for hints when you get stuck. Thank you to all the assistants and TA's who put in so much time to this course!
Now, for anyone who is debating taking this, having a calculus and linear algebra background will definitely help you in this course for the theory, but it's not a necessity at all. Some prior Python experience is needed as you will need to understand how functions are being called, but that wouldn't take a lot of time to get caught up on, but would require additional effort.
por Justin T•
11 de oct. de 2018
Fantastic course! As someone who has done several online tutorials that use frameworks like TensorFlow or Keras, even having implemented things like deep reinforcement learning agents and image classifiers with these frameworks, I've never really gone through any formal training on much of the lower-level concepts/mathematics of deep networks. But this course cemented a lot of the fundamentals about deep learning into my brain that I was missing before, organizing topics in a clear and concise sequence of videos/lessons that really helped me keep things organized in my own head. Doing the exercises in a "manual", framework-less way using just standard Numpy was an awesome and enlightening experience too!
por Balachandran S•
16 de oct. de 2017
One of the best Deep Learning courses (probably 'THE' best) around. Been a fan of Andrew Ng's sessions after I took his Machine Learning course in Coursera.
The course is perfectly designed such that its complexity increases gradually every week. The instructor makes sure that the participants follow completely.
Some points about the course -
1) Assignments are made too easy (too much hand-holding). But maybe the others who are new to programming might appreciate it better.
2) Andrew laboriously reiterated the points that required understanding.
Sometimes, I felt the course topic to be highly repeatative but later after completing the assignments, I felt it was required to be so and it was totally worth it!
por Shanmuga G•
20 de may. de 2021
First of all, thank you so much for this course I find this course very useful, I get to know more things. I would definitely recommend this course to my friends and colleagues but only if they are interested and also love to do math stuff because a non-math lover can't get much from this course, obviously the mathematics section of this course was tough to understand and had a bad time in deriving those algorithms and programming. I would also like to state that the quiz and examination section of this course is harder no hardest and that's completely opposite in terms of difficulty like you'll figure the teaching part was easier than understanding and the understanding is easier than programming stuff.
por Vishnupriya V•
17 de may. de 2019
As a beginner who is interested in Deep Learning, this course was very useful an informative. The explanations given by Prof. Andrew were to the point and precise. However, detailed explanations behind the mathematics(calculus) could've been given as optional videos. The quizzes and the programming exercises were also very challenging at a beginner level. They quizzed us not only on the equations but also on the concepts. The only drawback in this course that I faced was trying to submit my programming assignment through Jupyter notebooks. They can very annoying at times. Also, the discussion forms were very active with the mentors and fellow student who would quickly help by replying to your questions.
por Steve S•
3 de dic. de 2017
This course is a very thorough introductory review of neural networks that doesn't require expert level knowledge in some of the underlying math like calculus, but nevertheless manages not to talk down to you. In fact, the straightforward way the material is presented inspired me to learn calculus on my own to back up the material. Regardless, it gives you (almost) everything you need to start coding neural networks on your own. Where I did have some trouble it was owing more to lack of experience with Python and the Jupyter environment. I also would have liked a little more visibility into the data we were inputting, although I think that may be covered more in classes further on in the specialization.
por Mohit A•
22 de ago. de 2020
Hi to all team who had put their Mount Everest's height like efforts for making this a fab course and self explained assignments.And special thanks and love for my dear Andrew sir for teaching too smoothly and always relaxing their students by saying "If you don't get it,don't worry, we will see it after sometime".One more Special credit and mention for team who built these amazing self explained and too easy to understand python notebooks so that even a kindergarten student can get this and one only needs to pay attention on making skills and not on other things like how to fetch data,and how many and which libraries to be added etc.
Thanks and kudos to all team and loads of respect to DEAR ANDREW SIR.
por Arnaud S•
29 de oct. de 2017
I found this course absolutely excellent. The structure and approach are absolutely great, and I am very happy that you force students to understand the mathematical underpinnings of backpropagation instead of letting a DL framework do the heavy lifting for you. Engineers need to understand what they do deep down.
My only improvement suggestion would be to provide a more detailed explanation of why we do the matrix multiplication & transpose in the computation of dW and of dA[l-1]. It turns out that in the case of dA[l-1] the explanation goes to the heart of reverse-mode differentiation and how to avoid combinatorial explosion. Cfr's Colah's blog excellent paper on backpropagation for details.
por Simranjit S P•
19 de ene. de 2020
I liked this course very much. I have done coding and trained models in Pytorch and didn't have strong grasp in the math's part i.e Gradient and derivates that is the why i have taken this course at the first place. Though the course doesn't contain everything but it has given me enough knowlegde to start with deep-learning.The quiz and programmning excersice are really good. I have to think enough at some part and have done mistakes many times but got my concepts cleared. And thanks to coursera team for approving my financical aid.And though review may be good or bad depending on the person but i have learnt what i want to learn and it is good enough rahter than youtube or online material.
por Mukund C•
13 de sep. de 2019
Absolutely Fantastic. I thought the programming assignments were a little too easy, but that's probably because I am familiar with python programming. I must say that the structure of the code really helped me focus on the core algorithms and vectorization (using numpy methods), so, in retrospect, it is probably a good way to make the student focus on the core concepts. I wish, however, there were some (more) optional lectures on the math and some more detailed derivations and some "optional" practice problems on doing partial derivatives etc., just to cement some important concepts such as back propagation. Highly recommend this to students wanting to learn the basics of neural networks.
por Koravith T•
24 de feb. de 2022
I gained so much valuable knowledge from this course through the weekly Assignments. Learning by doing is real. The lecturer prepared exciallent materials especially the programming assignments that give us clear guidelines step-by-step, making it easier to understand. He took the effort so much to prepare the course. Additionally, he explains all the complicated points clearly including the derivation of various equations that require calculus knowledge which I did not expect to see him explain. Hopefully, I will be able to find time to take the rest course in this series to find some ideas of neural networks and deep learning that can be implemented in my master's and Ph.D. research.
por Greg A•
5 de sep. de 2017
Awesome course. I have fairly little previous math experience though I have been working on some calculus and LA immediately before/while taking this, and all the topics were easy enough to understand how they are supposed to work. Much recommend.
One small thing I think could have helped a bit is the practical examples do a little bit too much hand holding. It makes it a little hard to know if you are actually grasping the knowledge or just able to tell what to do based on what information has already been made available from the templates and such. Had to step outside of this and try to do some of it on my own to see which pieces weren't fully making sense. But still, awesome course!
por Yaseen L•
7 de sep. de 2017
Great, just like the first Intro to Machine Learning course Professor Ng distributed. Same style with improvements made in course design. For example, notation is much more consistent this time around probably because it is a more focused course unlike the first one. I would say taking Intro to ML first would help as it is a perfect primer for this course. Also, I'm glad they've decided to use Python which is just much more general purpose than MatLab. I would also say a solid grasp of the language is needed as a lot of boiler-plate code is provided and understanding it could be difficult if not otherwise comfortable with Python. Looking forward to continuing the full specialization.
por Borut H•
16 de mar. de 2019
Amazing course! The creators are very good teachers. Materials have the right mixture of motivation, real world examples, theory and practice. I also like Andrews presentation style - one can really feel that he truly cares about the students being given good information and getting encouraged to learn. The assignments were also very well made - everything works, the code is good and there is so much help in the context/comments (eg. someone could even finish the labs without understanding the subject) - but this basically allows each student to choose how much effort he/she wants to put into the subject (also meaning how much knowledge she/he wants to absorb during this course...)
por debraj t•
29 de abr. de 2018
I found this course very helpful in furthering my understanding and clearing a few doubts that I had from the Machine Learning course. I seem to understand back propagation much better now.
This course also helped me give a structure to the steps involved in actually building a Neural Network... gives me more confidence.
My only issue was with the programming exercises. I felt they were very tightly structured, maybe because of the automated grading system. It was almost impossible to go wrong. More flexible and open exercises, I think, will help in learning the real intricacies of building a NN from scratch. Don't really know enough to comment on how this change can be incorporated
por Chitra V•
9 de ene. de 2019
The course is well structured and the programming exercises are so detailed, I am going to refer to them in future while implementing neural networks. The best part about the course is, Andrew Ng actually taught the math behind the network. Rather than taking his students through a library function for neural networks in python, he taught his students how to code from scratch while also covering nuances such as suitable activation functions for different cases and ideal values for weights. The documentation for programming exercises is very detailed and must have taken plenty of time for those who worked on it. Recommend it for anyone wanting to start. Kudos to the instructors!