Deep Learning Prerequisites: The Numpy Stack in Python (V2+) (Udemy.com)

I think this is a great course for beginners who do not have a background in this material. Read the course description carefully. This is NOT a detailed study of NumPy or SciPy or Pandas or Matplotlib, etc. This is a general, broad brush strokes type of course to introduce you to what DL, ML, and AI are about. Taking this course can let you find out...yes, I really like this stuff. I want to get into this...OR it can show you that this really isn't your cup of tea. Put the author into the Udemy search box and see what other courses he is teaching. These courses are the courses you are going to have to take if you want details. Again, this is a great course for beginners who want a very general course with broad brush strokes. I can tell the author knows this subject area very well.

Found the first half of the course worthwhile while the 2nd contradicted some of the things said in the 1st half. At the time of this review this course is 6 years old and Python 2 has been post end of life for 3+ years. While there is worthwhile material in this course, it is in need of updating. Would have also liked to have seen answers and explanations to the exercises. Some can be found in the Q&A, but all don't explain the answer. While the last 2 sections do give guidance on a learning path, the courses and page references are out of date in the videos. They also appear to have a marketing slant to them. Section 9 is about setting up you environment and should have come at the beginning of the course instead of the end. Overall the first half was good reinforcement of concepts needed for Machine Learning. I would suggest checking out https://deeplearningcourses.com/ to see if there is a more current version of this course.

I think, what made this course so special, is just how the instructor tried to explain machine learning concepts in "the simplest way possible". The instructor did not go into more advanced functions in Numpy, Matplotlib, Scipy, Pandas, and SKLearn. He just explained enough to show you "how these simple operations and functions will become the basis of more complex machine learning/deep learning models". The instructor also went further into explaining the applications for each library for ML/DL to motivate you to learn further. So, if you are looking for a "complete/deep explanation of Numpy/Matplotlib/Scipy/Pandas/SKLearn library", then this course is not for you. But, if you are looking to understand "how these simple functions will be used in complex ML/DL models", then this course will answer your curiosity.

I have taken Lazy’s courses in past and he does not spoon feed. His style of teaching is actually encouraging and intuitive at the same time. Lazy does not try to impress. He is one of the most straight forward teachers out there, who gives you the truth. He does not spoon feed and he encourages hard work contrary to his alter ego! :) While his courses are methodological, they demand a lot of work by students and that is very helpful!

Great course with basic and general information that stands as a prerequisite to machine learning. - A bit stuffy to go through and rigid at times (I did not save the numpy link from the first videos and I was trying to find the colab links ). - I tried to comment in the exercise parts so we could have references and something to build on. Although I've written only slightly negative comments so far that is should be take in a constructive manner (if time permits as improvements for the future), overall the course is amazing and I highly recommend it.

It'd be perfect if I could have the solutions to the exercises. I've done all of them, but I'm not sure if there is a better way of doing them and it's up to you to see the solutions before solving them. I'm thinking on continue with the next courses but I'm doubting because the solution may be not provided (I like to work hard solving the exercises, but once I've done them, I'd like to check other possible solutions, specially the one from the teacher)

This is a good first view of these fundamental Python libraries needed for this instructor's Machine Learning courses. It is by no means an attempt to cover most or even half of the functionality in these libraries. It's enough to get you started and using the docs. Since it's free and short, it's worth going through the videos and trying the exercises. If you already know the basics of NumPy arrays, how to plot basic charts with matplotlib, e.g. then you could probbably skip this.

For the most part the course was good, better than some I have seen on Coursera. I believe this would benefit from more exercises throughout the course and solutions to the exercises. After having completed most of the exercises, we started getting into aspects which were not covered in the course material and were rather uninteresting to me, reading images and displaying them.

I haven't seen other courses like this one, and I've been doing a lot of them (DataCamp, Elite Data Science, Python, playing with Jupyter notebooks by others etc). I didn't realize how important a thorough treatment of the fundamentals was until I took this course. If you are willing to face a "gap analysis" on your knowledge, try this! Still finishing the last two exercises. This course showed me: 1) I need to brush up on my Linux command line skills. I am also going to jump out of Jupyterlab for a while and get into the nitty-gritty. 2) The importance of being able to program mathematical models from a low level (which indicates true understanding) to establish a substantial base knowledge. It's not the ultimate goal, but putting your underwear on last doesn't make you a superhero. Fundamentals first. 3) The need to take a long, tenacious view of my development in the field. There are good courses out there, but "good" is the opportunity cost of the superlative "best". Stick with the best every step of the way. 4) Embrace and deepen my facility with mathematics 5) If I want substance in my work, it will require preparatory... work! Many, many thanks Lazy Programmer. On to the next course! Tomylee

It's a good free beginning to all of his other deep learning courses. It was nice of him to make this course free, so that in future courses, we don't have to spend a lot of time learning this stuff over and over again. The course is very mathematically advanced and assumes that you know your linear algebra and probability theory. It's a good preview of what to expect in future paid courses. I'd totally recommend it as a starter course (especially since it's free). If you meet all the mathematical prerequisites, you'll find this course very useful for machine learning and possibly other uses. If you aren't mathematically adept enough to understand what's being coded, then this course serves as a warning to hold off on signing up for the subsequent paid courses (assuming that you don't read the course descriptions of any of his courses). It appears that a lot of thought, consideration and work went into the design of all this instructor's courses and course roadmaps. Therefore, I strongly recommend this as a starting point to anyone thinking about machine learning while also meeting the mathematical prerequisites.