The codes can be explained in videos rather than giving them in texts in the open lab. This can make coding even more understandable and applicable.

i would prefer to be more practical, and the lectures to be step by step on how can practice machine learning in real dataset (problems). I see that generally coursera emphisises in the theory rather than practical.

When I came up to the assesment I quit, because I had to spend so much time to understand how the framework works.

I would say that is a course with traditional acadademic lectures, which is not my type.

The course walks you through the concepts and way of thinking however they leave the explanation of the technical parts out

Course is extremely long. Good luck getting through Week 1 and finishing it afterwards.

This course is definitly not for the beginers. But can give you some basic understanding about the terms used associated with machine learning

Not a comprehensive course.

Dear [Coursera],

I hope this message finds you well. I wanted to take a moment to provide feedback on the Introduction to Machine Learning course that I recently completed. This course has been an enlightening journey, and I wanted to express my thoughts and appreciation.

First and foremost, I am extremely grateful for the effort you've put into designing the course content. The way you broke down complex concepts and explained them in a clear and approachable manner truly enhanced my understanding of machine learning. The blend of theoretical knowledge with practical applications through hands-on assignments was incredibly beneficial in solidifying the concepts.

The choice of teaching materials, including videos, readings, and interactive quizzes, was well thought out and greatly aided my learning experience. Moreover, the pacing of the course was just right, allowing for in-depth comprehension while also keeping me engaged and motivated.

I must also commend the accessibility and responsiveness of the instructors and support staff. Your willingness to address questions, provide clarifications, and offer assistance in a timely manner made me feel supported throughout the course journey.

As a result of your efforts, I now feel much more confident in my understanding of machine learning fundamentals and how they can be applied in real-world scenarios. This course has sparked a genuine interest in further exploring the field, and I credit that to your exceptional teaching approach.

Thank you once again for your dedication to providing a high-quality educational experience. Your commitment to your students' success does not go unnoticed, and I am truly appreciative of the impact you've had on my learning journey.

Best regards,

Tt was a fantastic learning experience. As someone new to the field, this course provided a solid foundation and understanding of the core concepts of machine learning.

The course content was comprehensive and well-structured. The instructors did an excellent job of breaking down complex topics into easily understandable modules. The use of real-life examples and case studies helped me grasp the practical applications of machine learning in various domains.

One aspect I truly appreciated was the hands-on approach. The course offered practical assignments and coding exercises, allowing me to apply the concepts learned and gain valuable experience working with machine learning algorithms and tools. The interactive quizzes and regular feedback from the instructors were also beneficial in reinforcing my understanding.

Overall, I highly recommend the "Introduction to Machine Learning" course on Coursera to anyone interested in getting started with this exciting field. It equips learners with a solid foundation, practical skills, and a clear understanding of the fundamentals. I am grateful for this learning opportunity and excited to continue my machine learning journey.

Thank you to the instructors and Coursera for providing such a valuable course!

Rating: ⭐️⭐️⭐️⭐️⭐️ (5 out of 5 stars)

Sure, I'd be happy to help you with a review of the introduction to machine learning!

The introduction to machine learning provides a fundamental understanding of the field's concepts and principles. It typically covers topics such as supervised learning, unsupervised learning, and reinforcement learning. Students are introduced to algorithms like linear regression, decision trees, and neural networks, along with the underlying mathematical concepts.

Additionally, the review often includes discussions on data preprocessing, feature engineering, model evaluation, and the importance of training and test datasets. Practical examples and case studies help learners grasp how machine learning is applied in various domains like image recognition, natural language processing, and recommendation systems.

Overall, a well-designed introduction to machine learning equips learners with a solid foundation, preparing them for more advanced topics and real-world applications in this rapidly evolving field.

Amazing course! - Lots of complicated ideas and concepts are presented in a clear way eg multi-layer perceptrons, Convolutional Neural networks, LSTM etc. The videos are professionally done with lots of clear diagrams, the videos come with transcriptions and many come with PDF slide notes (although the last few in the course are missing PDF slide notes, which would have made my note taking easier) There are several lab exercise assignments at the end of each module. One down side is that the graded exams and quizzes don't come with full explanations of why the correct answer is correct or why the wrong answer is wrong. This would have been helpful, but that being said you do have 3 attempts at the exams and they take your highest score, so its not the end of the world if you mess up a few.

Wonderful course! The low-level implementation code to understand what's really happening and the high-level abstractions to get rid of boilerplate code and focus on the execution is gold! It helps connect back with the theory/intuition beautifully. Only recommendation I'd have is to have GPU backed notebooks so that the runtimes are fast. Assign 4B timed out so many times, I lost count. Running the same code with minimum changes on Google Colab was *extremely* fast and only consumed a very modest amount of GPU resources.

I was an engineering major at Duke, but never took any sort of computer science/machine learning classes because I didn't have time. This class was super straight forward. Everything just made sense. I don't know how to say it other than that. It was great to see how much of the math and signal processing things I learned could be applied to something like machine learning. Before this class, I had no clue what machine learning was, and now I feel like I understand the main gist and the basis for all of the math behind it.

It's a very informative and well structured course for beginners. All instructors has made the entire course easy to understand with various real life examples and implimentation. I am very grateful to Duke University to come up with such an introductory course and I am thankful to all the professors of the University to make it easy for a beginner to understand and follow. And lastly I applaud for the coursera team for providing educational platform and resources for the learners.

very helpful course and all teachers are very expert and their teaching method is also simple but very helpful. I'm happy to take this course.

Thanks.....

Shivam Tyagi

Really loved this course. Duke university and the course instructors has done a great job in compiling and presenting this course. This course really is a gateway to the vast and ever developing world Machine Learning and AI. The use of real world examples and latest methods along with presentation of history of ML makes this course provides a solid understanding of ML basics. Best courses one take to get started in the field of Machine Learning.

In my opinion, this is an excellent way to be introduced into Machine Learning. The course concerns itself mostly with exploring concepts and the theory behind the most simple and representative neural networks of the last 20 years. Also the explanations are developed with excellent visual material and there are some PyTorch labs provided with the intention to give an insight to the development side of machine learning models.

Excelent course. However, it would be a better course with more REAL LIFE examples of applications of the models. In other words, in the sections where it is explained a LSTM put words in vectors and make the operations with a set of words. I know there was an example like that but it was very simple. The Model LSTM is very difficult so it would be nice to have an example more extended and described. Thanks.

This course helped me to understand the complex concepts in very simple manner. After finishing 70% this course, I felt confident enough to join Masters of technology in Artificial intelligence. During this course, I did not have to give extra time to anything other then the lectures.

I would like like to thank Duke university team for their efforts to make this course so precis and yet simple.

I loved all the materials in this course. I was specially surprised to see more deep learning materials then ordinal materials in machine learning like decision trees or SVMs in this course. Maybe the name of the course could be changed into introduction to deep learning which is more suitable for the course materials. Thanks a lot Coursera and Duke university for these fascinating topics

I am very happy to be a part of this amazing course. I was looking for it, and this course taught me more than my expectation. It gave me a tough time, but I manage things successfully and finally got my certificate. I would like to mention that professor Lawrence Carin was absolutely amazing throughout the course. I really thank him for his stunning contribution to this course.

Complexo, porém, muito rico em informações para quem está iniciando. Obs.: Para quem não domina totalmente o idioma inglês (Eu), poderá ter dificuldades na compreensão de alguns conceitos devido a legenda não acompanhar (tão bem) o raciocínio do professor, então, vale pausar o vídeo ou retornar quantas vezes for necessário. Obrigado pela oportunidade e sucesso a todos!

~Solid conceptual explanations

~Week 1 lectures were a bit repetitive given the video format and the ability to rewind/fast forward

~While recognizing that the Week 4 reinforcement learning section is unfinished, some may find step-wise (or iterative) examples to be useful in explaining Q learning especially for explaining the importance of alpha and non-myopic terms

Very nice introduction to machine learning with great exemples and teachers. Each lab time (1h each) was overly underestimated in my case for a newbie, 1h would translate into half a day or a full day. And I think a lot more could be explained about PyTorch coding exemples given in the labs, like the choices for filter size dimensions, but overall it was doable.

Really well done. The instructor not only obviously knows the material backwards and forewords but evidently also great teaching practices. Each module is one idea explained clearly with good visuals. He reviews and summarizes material. If you want to understand the theory and innards of machine learning algorithms this is a great course for you.

Overall, it's a good course! But I strongly suggest that the title of the course should be changed! It is NOT introduction at all... It goes deeper like Deep Learning, Neural Network, CNN, NLP and PyTorch, and even further like reinforcement learning, Q learning for the bonus lessons. Again, it is a good course, but the title seems confusing.