It is good, there is such extensive course online and free. I will use the Pros/Cons system from this course for my review of this course: Pros: - it covers a lot of topics in ML - good to gain overall general knowledge about ML - I liked recap of previous lectures at the beginning of next lectures, it is good to know how lectures are connected - I liked summary for each algorithm at the end of lecture, what is it good for, how performant it is, how useful/popular it is, what are it's weaknesses - may be I would give it at the beginning so viewers will be curious about algorithm for the whole video and not after video ended - I liked how different approaches were applied to the same dataset (Iris flowers), so results could be compared - simple topics (eg. decision trees, testing methodology, ... ) were explained clearly and in understandable way Cons: - complex topics (eg. neural networks) were explained in too shallow and anectodical way, like if you speak to someone, who already knows, what is it about, so they are not possible to understand from this course - sometimes it is not going from simplest to more difficult, but opposite way - starting neural networks with artificial neuron and its relation to human neuron is just fail (this can be said, when neural networks are explained) So overall B-. A lot of topics covered, good knowledge shared, however some pedagogical mistakes makes this course occasionally not understandable.
Great question! The material is a bit different, but there is a lot of overlap. I tried to make this course more applied. In particular, there is a set of 3 lectures at the end on how to apply machine learning in the real world. Of course, it's hard to compete with Kilian in terms of the delivery, but I'll try to meet the high bar that he has set :)
There is a lot of overlap with a typical ML course, but I tried to focus more on applications. In particular, there is a set of 3 lectures at the end on how to apply machine learning in the real world.
I was moved with this intro...but please do i need any basic knowledge in programming?, or what are the perquisite to learn ML. Thanks for your quick response.
The course syllabus: canvas.cornell.edu/courses/19987/ The class uses the book ESL. If your math is not that strong, or it has been a while since using calculus, you might want to start with ISLR. ISLR is in R but there is a github companion in python, which in my opinion is more practical in the working world (this can also be easily debated). I find python easier to start out learning because it has a more "english" feel to it.
Thank you for providing these materials for free!!
Hi just wondering do you have the slide/notebook shared as well? i think it will be great to have. Thanks!
Yes! All the materials are now available here: github.com/kuleshov/cornell-cs5785-applied-ml
Thank you for your patience.
@@vkuleshov its been 1000 thousands year..... Joke aside, Thank you very much for this!
Amazing course. If possible, could you please make courses on applied DL and RL as well ?
Thank you for creating this amazing resource!
It is good, there is such extensive course online and free. I will use the Pros/Cons system from this course for my review of this course:
Pros:
- it covers a lot of topics in ML - good to gain overall general knowledge about ML
- I liked recap of previous lectures at the beginning of next lectures, it is good to know how lectures are connected
- I liked summary for each algorithm at the end of lecture, what is it good for, how performant it is, how useful/popular it is, what are it's weaknesses - may be I would give it at the beginning so viewers will be curious about algorithm for the whole video and not after video ended
- I liked how different approaches were applied to the same dataset (Iris flowers), so results could be compared
- simple topics (eg. decision trees, testing methodology, ... ) were explained clearly and in understandable way
Cons:
- complex topics (eg. neural networks) were explained in too shallow and anectodical way, like if you speak to someone, who already knows, what is it about, so they are not possible to understand from this course
- sometimes it is not going from simplest to more difficult, but opposite way
- starting neural networks with artificial neuron and its relation to human neuron is just fail (this can be said, when neural networks are explained)
So overall B-. A lot of topics covered, good knowledge shared, however some pedagogical mistakes makes this course occasionally not understandable.
Hi would you please suggest me a hands on course plz
Could you post the homeworks/Assignments ? please🙏
thank dr. Kuleshov . will you share the code examples and slides to public as well and where
Yes, all the materials are now in this Github repo: github.com/kuleshov/cornell-cs5785-applied-ml
Sir,Can you share some resources to learn the Applied ML like some standard books like you learned from because great explanation on Ml thank you sir
any link for notebooks ?
Yes, all the materials are now in this Github repo: github.com/kuleshov/cornell-cs5785-applied-ml
link for notebooks pls
Yes, all the materials are now in this Github repo: github.com/kuleshov/cornell-cs5785-applied-ml
Lecture 19. Part 2 is missing?
Can you explain a little bit how this course is different from Machine Learning for Intelligent Systems CS4780/CS5780
Great question! The material is a bit different, but there is a lot of overlap. I tried to make this course more applied. In particular, there is a set of 3 lectures at the end on how to apply machine learning in the real world.
Of course, it's hard to compete with Kilian in terms of the delivery, but I'll try to meet the high bar that he has set :)
great effort .thanks
Difference between machine learning and applied Machine learning?
There is a lot of overlap with a typical ML course, but I tried to focus more on applications. In particular, there is a set of 3 lectures at the end on how to apply machine learning in the real world.
@@vkuleshov thank you so much
I was moved with this intro...but please do i need any basic knowledge in programming?, or what are the perquisite to learn ML. Thanks for your quick response.
The course syllabus: canvas.cornell.edu/courses/19987/
The class uses the book ESL. If your math is not that strong, or it has been a while since using calculus, you might want to start with ISLR. ISLR is in R but there is a github companion in python, which in my opinion is more practical in the working world (this can also be easily debated). I find python easier to start out learning because it has a more "english" feel to it.
That's right: you should be reasonably good with basic linear algebra, probability, and programming
1.25x his energy increased
link for notebooks pls
Yes, all the materials are now in this Github repo: github.com/kuleshov/cornell-cs5785-applied-ml