The course was thrilling with a lot of hands-on activities..but the downside was that there were errors especially in the second and last hands-on and those bugs are so annoying giving the fact that some of us are still new in the big data world and have no clue to solving such problems

It should have been made clear that good experience in Spark is required for this course. I struggled with most of the commands and had to watch, re-watch most Spark related videos, google meanings of commands etc. The course experience was not very pleasant. Nevertheless, thank you.

The virtual machine in this course no longer is functioning. PySpark update seems to not play nice. I think the content also needs some updating for more modern machine learning techniques.. like using big data with deep learning systems like tensor flow or PyTorch.

I expected course with more in-depth and more difficult examples, I learned about a few new concepts, most methods were repetitions for me.

Machine learning is too simplified and spark part is not even explained, also very little relation of all course with Big Data.

Considero que está algo desactualizado el curso y las herramientas de aprendizaje. Tenía mayor expectativa

Almost a useless course - ML overview using KNIME which gives no insight whatsoever.

Too basic

The course content is very poorly explained. The quiz questions don't really test what was taught in the lectures, and the assignments are just copying and pasting things. I feel like I still have a very poor understanding of what was supposedly covered in the course. I cannot generalise or apply the 'learned' information or skills to other topics or researches because I didn't actually understand the core concepts or how to use the programs.

This is another course in UCSD's "Big Data" introductory course. The material is not pertinent to a specialty on big data technologies. Further the course does not increase one's knowledge of Machine Learning in any way that justifies spending the time in the course.

T​he VM software provided is now out of date. The use of a clunky GUI-based tool (KNIME) seems like a waste of time--not likely to be useful in real applications.

Regression is least bothered, less hands on

cloudera vm doesnt work well