Data Science: Deep Learning and Neural Networks in Python (Udemy.com)

I was exited to take this course but when I faced the Deep Learning Readiness Test, I was taken by surprise. I couldn't do a singe equation. I had read the prerequisites but this course expected a much deeper understanding about calculus than I expected. So yeah, I can write neural networks now, but I still don't understand the "why" behind the math that you tried to teach me. Throughout the whole course you said "try to do this yourself first" where I (with increasing feelings of guilt) just skipped to the answer right away every time. The math was way to much for me anyway, plus I have this deadline coming closer (I have to implement this stuff for a school assignment in a few weeks). Your teaching skills are amazing, as well as your documentation and your understanding of why people want to take your courses (i.e. explaining where the math equations come from). However, please find a way to put a Readiness Test in the prerequisites because I have actually learned very little from this course.

Very useful course. I get the skills to code my own NN from the scratch using python only. Now I am sure I can do it without looking up to this course. The author does a very good job of insisting you do things by yourself. And it is really important to fully understand a topic and acquire the skill. This course is a must for any more advanced NN course. I started from advanced NLP, and finished it but had a really hard time figuring out what is going on inside the model. This course sorted 90% out for me. What to improve some formulas conversion might be described better, I was stuck in a few places, but nothing I couldn't sort out without google.

Just ended the core part of the course. For me it was a perfect oppurtunity to learn more about basic concepts of Deep Learning that were not properly explained during my AI classes. I think the strongest side of this course was to not learn syntax and oblige to write ANN using numpy. It was totally a new experience for me and finally allowed me to understand basic concepts. My level before course: I could use several API and I knew the concept of backpropag but I was not capable of calculate this on my own.

This course is perfect match for those professionals that want to enter the world of deep learning from explanatory aspect. The best thing is instructor approach towards the content of the course and precise way of explaining topic with including every step in both math and programming path. This course will definitely provide some initial knowledge about how neural networks work and why are they used for. the only thing is that this basic knowledge about neural networks should be improved with further research and practice by professionals that took this course. At the end, special gratitude to the instructor for forcing me to review math (calculus) knowledge from university. It is something that does not hurt and by contrary it is only useful.

This is going to be the longest Udemy course review I've written thus far. The executive summary is thus as follows: I am very glad I took this course. The course is the third in the Deep Learning track after the Linear and Logistic Regression courses, so you should either have taken them or be familiar with the material before attempting this one. The core topic of this course is backward propagation, which is a fancy name for gradient descent. However, you should not underestimate the math involved -- it gets very complicated. If you are familiar with undergrad calculus, particularly how to solve for derivatives using the Chain Rule, you won't be learning too much new math. That does not mean the math you'll be doing is simple or easy. It is neither! You will be calculating gradient descent for the Sigmoid and Softmax activation functions and the instructor insists you do them by hand -- calculations that can take days for you to do correctly. It's a whole different ball game from deriving linear regression equations. A matter of uncertainty I've had for a while that this course cleared up for me is this: Sigmoid is used for binary classification, whereas Softmax is used for multiclass classification (K = 3+). If you have a job interview in a month, I'd recommend for you to review at least this course and maybe even Logistic Regression because unless you have an eidetic memory or manually calculate Softmax gradient descent on a weekly basis, there is no way you will remember how to do any of the math. Personally, though, I cannot imagine any real-world scenario in which you would actually need to unless you’re implementing your own ANN from scratch. It's mostly important that you understand the concept of what it means and how it works. That is what I learned from this course, and I'm very grateful that the instructor took the time to flesh out the math for us. With that said, if there is one component I feel missing from the course, it’s a walkthrough of Softmax derivation with a sample dataset. The instructor was kind enough to supply some supplemental materials in the appendix lectures, which are indeed very helpful, but I was so hoping for an actual walkthrough along the lines of the Feedforward in Slow Motion lectures in which we applied Sigmoid derivation on a small dataset. Given that backprop is the crux of the course and the foundation of more complicated neural networks, such as CNNs and RNNs, I feel it is super important to get the concept really drilled in with actual numbers and not just k primes and y primes. Even so, I'll probably need to review this course if I ever plan on interviewing for any Deep Learning position. Again, to sum up, this is a very good course -- perhaps the most math-intensive of any AI/ML course I've ever taken. If you're serious about learning how to build ANNs from the ground up, this course is for you. You're probably going to feel very stupid, but you'll be glad you took the time and stuck with it.

Definitivamente es un curso que recomendaría, sin embargo, como lo deja bien claro el autor, es necesario tomar los cursos de prerequisitos (Linear Regression y Logistic Regression, si no tienes fundamentes en programación también requieres los cursos de Python que también imparte el autor) para lograr comprender lo que aquí se aborda. A diferencia de otros cursos, no presenta las redes neuronales como una "caja negra" sino que plantea las matemáticas detrás de las redes neuronales para que puedes comprender lo que está sucediendo. Este curso no es fácil de digerir, se requiere de tiempo y muchas veces revisitar los conceptos.

This is an amazing course to kickstart your foray into Machine Learning. As LazyProgrammer himself puts it, most courses out there will merely teach you how to use APIs, but not actual Machine Learning! I am just grateful for having taken up this course and also wish that i had taken it up earlier! One suggestion(not specific to this tutor alone) - It might be more fun and also beneficial for learners if courses on Udemy also have a final project to evaluate learners. Thanks, Anish

If You want to learn Deep Learning Come Here otherwise go away, other course teach you the API, but here we are studying Deep Learning in depth, after taking all the prerequisities and taking this course was able to write my first Deep Learning Model by my own, all in PYTHON with NO API only Numpy Stack, Thank Very Much Lazy, was Thinking Deep Learning was a hard thing to begin with, but Lazy Programmer make that thing simple as doing addition but for that you must take all the prequisities first and put time in it 5 stars++++++++ Now Next Step Modern Deep Learning==> Convo==>LSTM

I am so glad to have discovered the entire machine learning series worthy of my time. Admittedly, I watched several free videos and wasn't very impressed by the lack of substance. Then, I saw the advanced math prerequisites in the course outline and I decided to give it a try. And, boy, I'm glad in the investment because it is so satisfying to derive the equations and actually see results in code. I have since watched and re-watched the whole video several times, while gaining insight each and every time. The fact the course has been updated with new materials is a strong indication the lecturer cares about completeness and the content is brilliantly laid out. While you many not get it on the first go, the reward awaits those who are willing to put the time and strong perseverance. There's no free lunch here.

This is a great intellectual exercise for your brain for sure, it should recognize the pattern... Actually it is great if you can take the course with swiftly moving forward to grasp general concepts and then use backpropagation technique to study the details more carefully (e.g. refresh you calculus skills). I wish though more explanations were given on the way not just typing along the code, maybe taking the code still and explain what's going on would be better. It gives immense amount of complex information to think about and ideas how to implement it.

Theoretically a good course .

But lacks a full time practical use case.

Mathematics is not easy to understand. I want my money back.