In the AI for Scientific Research specialization, we'll learn how to use AI in scientific situations to discover trends and patterns within datasets. Course 1 teaches a little bit about the Python language as it relates to data science. We'll share some existing libraries to help analyze your datasets. By the end of the course, you'll apply a classification model to predict the presence or absence of heart disease from a patient's health data. Course 2 covers the complete machine learning pipeline, from reading in, cleaning, and transforming data to running basic and advanced machine learning algorithms.In the final project, we'll apply our skills to compare different machine learning models in Python. In Course 3, we will build on our knowledge of basic models and explore more advanced AI techniques. We’ll describe the differences between the two techniques and explore how they differ. Then, we’ll complete a project predicting similarity between health patients using random forests. In Course 4, a capstone project course, we'll compare genome sequences of COVID-19 mutations to identify potential areas a drug therapy can look to target. By the end, you'll be well on your way to discovering ways to combat disease with genome sequencing.
Get you started with the basics. Explanation is great but some topics are only covered by referring you to the documentation. Lab solutions helped fill knowledge gaps not covered in lectures.
I would have had more stars, but a couple of the programming assignments had different values for random used for the answer and not what was listed in the question.
Good introduction. A bit too short for a 4-week course. The autograder is not very good, and some solutions are wrong.
The topic is great, and the linkage and references provided are valuable.The hands-on quiz should be supported with better instructions and descriptions regarding what to do.
Showing: 20 of 23
The subject is interesting and exercises are educational but there are many shortcomings. Numerous assignments are broken and some answers in quizes are wrong. In the last one I have copied author's solution and even then I was 20 points short. Additionally, more than half of materials are just links to library documentation. The examples to work with are interesting, but those are almost exclusively the ones provided with sklearn library. I've learned a lot in this course, but I have a feeling that this is because numpy, pandas and sklearn are well documented, not because this course is well made.
The course has good content, but unfortunately, like some other courses on coursera, the assignments are unclear, or contain errors. as well as the support team do not answer questions. Making it difficult to obtain the certificate of completion.
The topic is great, and the linkage and references provided are valuable.
The hands-on quiz should be supported with better instructions and descriptions regarding what to do.
meskipun agak eror dalam lab penugasan tapi alhamdulillah sudah bisa
The course stars off well, but there is a steep learning curve and fast pace, with assignments often much harder than what was discussed in the classes or than what is reported in the documentation. Assignments could be written more clearly. However, the course does cover quite some basics on the field.
- A lot of typos in documents
- Concepts and features were poorly explained; the majority of the course is documents and files being thrown on the table for learners to crawl through with hardly any further instructions, making the learning curve super steep.
The Dictionary assignment in week 1 requiring 100% to pass has an obvious fault in the assessment process not allowing correct answers to be graded as correct
Nice course
nice
Good
This was a good learning experience for someone new to data science and scikit-learn. The resources provided in the modules were helpful and mostly relevant. Besides the course not including various other models from scikit-learn, it was a fruitful experience.
Get you started with the basics. Explanation is great but some topics are only covered by referring you to the documentation. Lab solutions helped fill knowledge gaps not covered in lectures.
Good introduction. A bit too short for a 4-week course. The autograder is not very good, and some solutions are wrong.
It could be better if we can see where we did wrong after each assignment. Good and well-paced course otherwise
its ok, good
The content is solid, but there are a nontrivial number of errors in the quizzes/assignments. Likewise, the programming labs cover good material, but the problem statements are sloppy and often too ambiguous to set you up for success with the auto-grader (which doesn't tell you where you lost points, making it arduous to determine where your assignments are failing for something like e.g. having your new columns added in the same order as the solutions).
pretty nice, even though the autograders were giving me a hard time on the labs. Good to brush up my panadas and scikit .
The second half of the course is not well explained.
Structure of this course is good in princilple. Quizzes are good to prove, what you've just learned. BUT the lab session are anoying to some degree. The grading is not working very well, even with a correct code (but maybe with a slightly different but correct solution to the problem). This gets annoying with the bigger tasks at the end of this course. The failures are reported frequently and for months...it seems not to help. I appreciate that they also do a lot of reading themselves, but not if I have to create an additional account to read it. Video expalnations and coding in the videos, sometimes were too fast for me... Unfortunately, I cannot recommend this course!
glitch in the programming assignment of week 3