Good intro course, but google colab assignments need to be improved. And submitting a jupyter notebook was much more easier, why would I want to login to my google account to be a part of this course?
Great course to get started with building Convolutional Neural Networks in Keras for building Image Classifiers. This is probably the best way to get beginners into Deep Learning for Computer Vision.
創建者 Jeremy V K•
Amazing class! As an absolute beginner, I wanted to learn machine learning and AI but didn't even known where to start. I even started a different machine learning course which I could not follow well, and expected similar results with this class. But this class, this class is aimed at beginners, no need for any pre-requisite knowledge and the google colab environment ensures that it doesn't matter what hardware you currently have, since its all done in the cloud. Also the practice notebooks are very detailed about each sections of the program. I'm not a master at machine learning, but atleast after this course I feel that I too can learn it.
創建者 Dhamotharan B•
I have used Tensorflow in my projects but never know some of the tricks which could improve the model.I was very dependent on transfer learning. But, now after getting to know much about Tensorflow, I feel so confident . A basic understanding of how model works with Tensorflow is essential and Laurence Monorey provides you some of those basic tricks and concepts of how neural networks works with Tensorflow. I can assure anyone here taking this course would definitely give a try to adjust the way they have approached towards implementing Tensorflow in their projects. Thanks Andrew and Coursera for bring up this initiative.
創建者 Prashant S•
I found this course very helpful because of working example at every step. First there is step by step explanation of each line of code after which you can play around with the code by making small modifications to it and observing results. It is not heavy on math behind machine learning but there are certainly lot of new terms. Most of time i googled those term to learn a bit more about those. Overall, instructor explanation is extremely good and easy to follow up. Its extremely important to play around with the code samples. All i needed was a browser and no installation on my laptop to finish this course.
創建者 Michael B•
I love the courses put out by deeplearning.ai. I previously took the 5 course deep learning sequence taught by Andrew Ng (which I would also recommend), and am VERY pleased with the first course of this sequence taught by Laurence Moroney.
The lectures are broken into small, digestible chunks. The quizzes are hit core knowledge points w/o any tedious "can you do this by hand" nonsense you see in some other courses. The notebooks provided in the course offer useful templates for adapting to other problems. Just amazingly well done in every aspect.
Looking forward to taking the rest of the sequence!
創建者 Pushpak G•
Excellent for any beginner. Watching Andrew Ng anywhere gives you a sense of authority and validates everything. But all the teaching part is done by Lawrence who is equally humble and knowledgeable.
All the theoretical topics covered are explained in brief but there are ample resources on the internet to understand them thoroughly.
The coding part is very easy to follow.Although some python code blocks were typical to understand but again you can always look them up on the internet.
Overall it is a brilliant course for anyone who wants to start with Keras, tensorflow, deep learning.
創建者 Prafull P•
This course is an excellent starter for people who want to learn about Tensorflow and how to use it to create neural network model very quickly . The Instructor explains every thing in very lucid language.Course is well organized to help you go from beginner to an intermediate quickly. Great articles and videos links will also come your way so even that would help you improve and enhance your knowledge. Highly recommended for someone who wants to learn about Tensorflow and enter into the field of ML & AI. A Big Thanks to deeplearning.ai for creating such course :)
創建者 Anirban S•
I love the following things about the course:
a. Very calm, consolidated, and well thought of introduction to TensorFlow. The documentation could be a little intimidating for a newcomer. But this course is a step by step guide.
b. The exercises encourage you to explore more. When you explore more, you learn more.
c. The workload is just enough and you can manage it with your regular course studies and student jobs.
What I wish I had a little more from this course:
a. I wish there was some element of NLP in this course. A little would have helped.
創建者 Victor A•
Great learning experience overall... Prof. Moroney was very patient in his approach and took his teaching one step at a time. So I never felt like I was taking too huge a leap at any particular one time. The links he provides for study were also helpful.
It was obviously a plus to have a great teacher like Andrew NG chip in occasionally a word or two.
Overall, it's a great course and I'd absolutely recommend to anyone interested in exploring the possibilities that computers of today give us in exploring our world.
創建者 Kirt U•
The course material and presentation is excellent. However some of the course tools are complete trash (code autograder in particular - this is because the code that was shipped off to the code autograder wasn't the code I had been working on - it wasn't until later that I realized that the tools were taking predefined [expected] file names and not the code I was working on - this is only year 8 of this otherwise excellent project - 8 years and the tools are still substandard). Also the quizzes are too easy.
創建者 Hannan S•
First of all, the course was amazing! I found it great for the following reasons:
- Laurence Moroney (Instructor) was very professional and clear while delivering the knowledge
- The introductions by Andrew NG were really nice
- Easy to understand codes and understanding of thr underlying principles
- Varied topics such as CNN, NLP & Time Series
- Very insightful by providing expert opinions about different ways of model optimization
I really enjoyed the course and I thank the instructor for the same :)
創建者 Curtis P•
Coursera and of course the instructors have really got this online teaching down to a science allowing students to cover often quite complex topics in an easy to digest and efficient manner. Even though it does skim the surface it does give a very good 10,000 foot view of the objectives and capabilities of the topic and technologies. To get same perspective on my own would be a lot of googling, trial and error, without the benefit of knowing 100% that I was covering the appropriate knowledge.
創建者 Pranav B•
Introductory level course. Perhaps the best feature of this course is that you start to learn by doing right from week-1. The instructor doesn't spend time explaining every line one by one with every detail. That leaves you to figure out a few things on your own due to which you're bound to remember these details. Notebooks are also much better than the deep learning specilaisation. I often found myself going through the tensorflow documentation - learning and exploring as I did. Fun course!
創建者 Gilles P P•
Cours intéressant, clair et facile à comprendre. L'enseignant est très sympathique et semble passionné. C'est également facile à comprendre même pour un non english native speaker.
J'ai déjà suivit les cours d'Andrew Ng et comme de nombreuses interview d'Andrew et des références sont données dans ce cours cela les rends très complémentaire.
On a qu'une envie c'est de continuer pour en prendre plus sur ce sujet passionnant.
Je suis très satisfait de suivre cette spécialisation
創建者 Rushikesh J•
Perfect Course, It tells you how to implement basic neural network to deep cnn.
Week 1 : Intro to tensorflow/keras
Week 2: building dense neural network; 2 applications fashion mnist and digit mnist
week 3: building cnn, improving accuracy on week 2 applications
week 4: using image generator to auto label the images, horse/human classifier and happy/sad classifier
Overall a perfect course to begin with, though i would advice to have basic understanding of neural network and its working.
創建者 Matthew E•
Although the concepts can be a bit technical, the explanations are very accessible. You learn how to implement ideas instantly, and by the end of the course, you are very well suited to experiment on your own. I'll be continuing the specialization. This, together with the deep learning specialization (which I have already taken) will I believe fully prepare anyone to work or do basic research in this field (at a fraction of the cost of a CS or AI undergraduate degree). Fantastic!
創建者 Sripathi S•
Very well structured course to get started with Deep Learning using TensorFlow. Laurence explains the flow of the programs and key concepts in a clear manner, which made it easy for a beginner like me to get familiar with the material quickly. Working through the problems without getting stuck in the theory was a fun way to see the possibilities of AI first hand and learn by doing. Highly recommend this course for any developers or programmers who want to explore deep learning.
創建者 HE Y•
This course should be considered as the inception of the Tensorflow when one steps into the field of deep learning. That would be very helpful to build a comprehensible network about this famous framework and how AI is applied to real life. I suggest introducing more practical work, for example, the video in the course, how AI helps the Africain farmers to know the health state of their crops. Using this case as an example might be more exciting from my point of view. Thanks.
創建者 Rishi G V•
The author, is way of teaching make me understand more into the fundamentals of the concepts. Now i have the strong understanding of these concepts with Good hands-on-experience.
But the current course i only audit, because of financial problem. If you provide me certificate for completion of these course it will be definitely useful for my career goal.
My leaning never going to stop , hereafter i will learn lot of courses from coursera with the financial aid.
創建者 Ahsun T•
Although while pursuing a higher degree in AI it was great to learn the minutiae of machine learning methods, this course seems to provide the best abstraction for a high level programmer - giving flexibility to play around with different datasets and GPU architectures and making it super intuitive and easy to apply it to your own problems. Let's build AI for solving problems where human decision making is limited It's really cool and you can make a difference!
創建者 Sourav S•
This course was very useful, especially if you gone through the deep learning specialization, which I did. The course starts with implementing a simple neural network, and then progresses onto convolutional neural networks. The course ends with a very useful data management topic on training data labelling. I would have found it useful if the course also focused on alternative attributes for the some of layers like Conv2D, the compiler, etc.
創建者 neil h•
Very well-balanced presentation. Started considerable fluency in python, advanced education in digital-signal processing, but limited experience with ANNs in general and tensor-flow in particular. With this course — and some background in Dreyfus 2005 and Haykin 2009 — I feel like I'm starting to get the picture. The hands-on was straightforwardly presented and extensible, with just enough wrinkles to make you think and stump the chumps.
創建者 Mateus d A D P•
This was a great course to learn how to use the basics of Tensorflow. The layers mentioned in the course are Dense (fully-connected layers), Convolutional, Pooling and Flatten layers. It also teaches you how to use callback functions during the training phase, as well as how to handle real-world images.
This course does not teach you about how to tune hyperparameters, but I wouldn't expect that from an introduction course.
創建者 Xiaonuo G•
Using https://colab.research.google.com/ is definitely a good choice because it saves the learners a big chunk of time setting up a deeplearning workstation by herself. The course's source code is commented extensively to ease understanding. Although the technical details and specific explanation of the deeplearning algorithms are pretty lightweight, it's more than enough to get one's hands dirty as a beginner course.
創建者 Dina M•
I really enjoyed the line-by-line code explanation and the right balance between theoretical and practical parts. As a beginner, it is easy to get lost in all different types of layers, optimisers, etc, and this course helps understand a general structure of a neural network program. The Python notebooks that we are given are extremely useful for watching how the things work by experimenting with code. Thank you!
創建者 Neel M•
This is an amazing course, and one can feel the hard work they have put into it. I was able to experience so much theory in practice, image augmentation, dropouts, transfer learning. Learning experience? Much better, it was a learning enthrallment! This is one of those courses which make deep learning looks so easy, and approachable. Highly recommended for anybody, and coursera should have more courses like this.