Cassie, I love the way you talk and the capability you have to communicate complicated stuff in a simple way! I am recommending your course to my colleagues even if they are senior data scientists. Thank you!
Excellent! This lecture is a paramount example for a core principle of (human) learning: Formulae are good for defining things, examples are much better for explaining things. How much time did I spend before to unravel simple truths from thickets of math lingo ...
I love you. You are brilliant. Thank you for explaining things the way you do...you have a beautiful understanding and the ability to share it with all of us. To be able to train under you would be the greatest gift. More classes please:) Keep shining and thank you again!
Definitely the clearest explanation of these concepts I've seen. Really excited to recommend all 4 parts to those at my company interested in AI/ML. Fantastic work, Cassie!
Wow! Congratulations for your curriculum and your hability to explain complex concepts like you are telling a story!!! I like so much the way you explained and the sequence adopted to introduce the ideas involved in those algorithms! You are so authentic! Wish you all the best! PS: I sent you a linkedin invite :D
The lectures are super fun due to your teaching style ! Although I am quite familiar with the content but feels like skimming through the lectures just for fun :D
The whole series was amazing, thank you Cassie. It's inspiring to know the concepts so well and then present it in such a manner, loved your style & sense of humor all along. Would like to know what books/resources you would suggest? I'm not asking only from a ML perspective but how to think of data itself eg: seeing how kNN can be sensitive to high dimensional data space or when you explained how if the perf varies wildly in a kfold CV split that's a serious issue etc...
Thank you for the well-structured overview of the key concepts and philosophy behind ML. Thoroughly enjoyed and inspired for the next year! I am still hoping to read your book on decision intelligence. I am planning to join your tribe! :)
Hello Cassie, This is brilliant. I have learned so much without neither being bored nor lost at any single moment. Thank you! P.S: Can we download the presentation somewhere?
Hey Cassie, Great session. I have a question related to the knn model, Is knn a machine learning model? Because it just predicting based on the given number of nearest neighbors. Is it really learning something?
It's an example of lazy learning (in k-NN, the model is the unsummarized training dataset, which is pretty lazy). Lazy learning is a class of algorithms that most authors are happy to include in ML textbooks, but some hate it and make the same observation you did. In my opinion, it doesn't really matter if it "counts" or not. What matters is that k-NN is sometimes a useful solution to machine learning problems and it's worth knowing about, so I included it in the course.
I'm a MLE but would want to review the whole course again already and recommend to everyone I know, thank you Cassie!
Excellent. You are a great motivation. Your articles, videos etc. reminds me "If you can't explain it simply, you don't understand it well enough.".
Cassie, I love the way you talk and the capability you have to communicate complicated stuff in a simple way! I am recommending your course to my colleagues even if they are senior data scientists. Thank you!
Excellent course and easy to understand. Thank you so much Cassie.
I am you big fan right now :) Thank you for sharing this awesome learning, Cassie :)!
Excellent!
This lecture is a paramount example for a core principle of (human) learning:
Formulae are good for defining things, examples are much better for explaining things.
How much time did I spend before to unravel simple truths from thickets of math lingo ...
Best explanation of the curse of dimensionality ever!
Thank You so much Cassie for this excellent course. You explained concepts really well.
Fantastic....thanksgiving algorithms. Nothing better. Thank you Cassie.
So brilliant explanations to understand all those algorithms intuitively.
Thank you, Cassie!
Thank you so much, Cassie, for this awesome course!
I love you. You are brilliant. Thank you for explaining things the way you do...you have a beautiful understanding and the ability to share it with all of us. To be able to train under you would be the greatest gift. More classes please:) Keep shining and thank you again!
Brilliant and intuitive explanations. Thanks for sharing these videos.
Thank you Cassie....it was a glorious ride through ML that you took us all for
Definitely the clearest explanation of these concepts I've seen. Really excited to recommend all 4 parts to those at my company interested in AI/ML. Fantastic work, Cassie!
What is a psychoanalyst's favorite mathematical function? 56:52 That made me laugh out loud.
Thank you for the brilliant course.
Great course. I learned a lot from Cassie. Thanks
Great work Cassie.
Love the sleek presentation!
really enjoyed the course ! thanks so much Cassie !
Thanks so much Cassie for this absolutely brilliant course , I really enjoyed it and shared it to my colleagues too !
Wow! Congratulations for your curriculum and your hability to explain complex concepts like you are telling a story!!! I like so much the way you explained and the sequence adopted to introduce the ideas involved in those algorithms! You are so authentic! Wish you all the best! PS: I sent you a linkedin invite :D
Your presentation is inspiring. Thank you!!!
Excellent course Cassie, thank you!
Great! Thanks for sharing Cassie!
Superb round off to this phenomenal 4-part series. So upset that it was such a long time coming but so happy it's out now :-D
Was waiting for so long for this. Thanks Cassie 😊
The lectures are super fun due to your teaching style ! Although I am quite familiar with the content but feels like skimming through the lectures just for fun :D
At last ! Part 4 is there…….thanks Cassie !
The whole series was amazing, thank you Cassie. It's inspiring to know the concepts so well and then present it in such a manner, loved your style & sense of humor all along.
Would like to know what books/resources you would suggest? I'm not asking only from a ML perspective but how to think of data itself eg: seeing how kNN can be sensitive to high dimensional data space or when you explained how if the perf varies wildly in a kfold CV split that's a serious issue etc...
Thank you for the well-structured overview of the key concepts and philosophy behind ML. Thoroughly enjoyed and inspired for the next year! I am still hoping to read your book on decision intelligence. I am planning to join your tribe! :)
Hello Cassie, This is brilliant. I have learned so much without neither being bored nor lost at any single moment. Thank you! P.S: Can we download the presentation somewhere?
Very clear thank you!
this is by far way easier to understand than my professor in my uni LOL
Hey Cassie, Great session. I have a question related to the knn model, Is knn a machine learning model? Because it just predicting based on the given number of nearest neighbors. Is it really learning something?
It's an example of lazy learning (in k-NN, the model is the unsummarized training dataset, which is pretty lazy). Lazy learning is a class of algorithms that most authors are happy to include in ML textbooks, but some hate it and make the same observation you did. In my opinion, it doesn't really matter if it "counts" or not. What matters is that k-NN is sometimes a useful solution to machine learning problems and it's worth knowing about, so I included it in the course.
Great mam❤️ from Tamilnadu,
Brain exploded with neural network
Minute 12:30. The explanation of the course of dimensionality is reason enough to watch the whole video.
Is it possible to add subtitles in English?