From which course you are learning. I also want to learn machine learning but not able to find which course is best for me. Cam you suggest me which course i should take?
@@kenconcepts Hello my friend, see, AI & ML are efficiency-based concepts, meaning they let a business remove repetitive business tasks/processes and automate them (to some extent) with the help of technology. This, in long term, is not just efficient, but also cost effective. But still, after so much development in AI & machine learning field, there are certain areas that they CANNOT add much value to, I'll recommend you to watch this video: th-cam.com/video/BZUHsuE2Rns/w-d-xo.html Hope this was helpful!
It may surprise some people, but logistic REGRESSION is in fact a regression model. The output is continuous: it's a probability. Of course you can dichotomize the output and create a classifier. Just like you can dichotomize any score function or regression model output. So the distinction between regression and classification is not so clear cut.
This is what Azure AI 900 course articles says - Note Despite its name, in machine learning logistic regression is used for classification, not regression. The important point is the logistic nature of the function it produces, which describes an S-shaped curve between a lower and upper value (0.0 and 1.0 when used for binary classification).
I always find it interesting that the statement "logistic regression is a classification method" is repeated so often, despite 'regression' being right there in the name. Like decision trees (CART), random forest and other similar methods, there are both regression and classification versions of the method. In a binary outcome problem, we model the process as flipping a coin that has a probability p of coming up heads (1) and 1-p of coming up tails (0). We can either predict p, a continuous value between 0 and 1, or we can predict the outcome, itself, which is in {0,1}. The former is regression; the latter is classification. Logistic regression predicts that probability p and logistic classification takes that probability and uses a cutoff (sometimes, but not always, 0.5) to predict the outcome. Many times, the probability is more important (for example, lots of the same type of customer -> you do not want to assume all of them are 1's, when p is estimated to be 0.6) and sometimes the outcome is more important (for example, making a decision to approve an application for credit.)
You are correct and the video misinforms about Decision Trees, Random Forest , SVM, and even Neural Networks - all of which have a regression and classification usecase.
I love how the explanation is made to everyone with experience or not in this issue. I’m in the second group and now I have a reference to start. Thank you ☺️
This would be a good video for the person who already understands the vocabulary of machine learning and the different aspects of machine learning. I didn't really gain any knowledge from this video since I'm starting from the beginning of ML.
Been trying to fully figure it all out for a while and here you were concisely explaining the key pointers in exactly 5 mins. Thanks for your help & keep on with the good job mate !
I find that you glossed over the details of the more difficult models. But provided examples and more depth for the simpler models. For individuals learning ML for the first time, there is a need for people to understand the more complex models in depth. I suggest adding deep dives into each specific model.
I was passed out just by thinking about my ML exam and this video boosted up my confidence I mean at least now I’ve an idea about that subject. Thanks to you
Interesting how many people in the comments call Logistic Regression a regression model... Logistic Regression outputs a category, not a continuous value. To understand deeper: Logistic Regression = Linear Regression + Sigmoid (or SoftMax for multi-class) + Unit Step function Thus, for the binary case, imagine the prediction of the linear regression (a continuous value from -infinity to +infinity) that is than squeezed into the range of 0 to 1, which is not a straightforward probability, but we can interpret it that way. Lastly, a unit step function is applied (the threshold), which makes the prediction categorical. So, while part of it outputs continuous values, the final outputs is categorical and Logistic Regression is always used as a classification model in the literature.
Great compilation. Very well presented. Clear explanation. One of the very few videos on YT that sums it all so well. It would have taken a lot of effort but worth it, benefiting so many, thanks!
Great primer on ML Models! I would suggest slowing down when you talk and also do a FINAL slide showing all the subcategories you covered under each Supervised and unsupervised models. I would also use real world examples of where each model is being used and applied today.
Thanks for explaining machine learning models with such precision, can’t believe it was so short... I can now decide and lead my team on best ml model to select!
Wow, thanks for kind words! I'm trying to create a course Peter, trying even harder to launch it soon. Once I have it live, I'll make sure to keep you posted. Thanks again for the appreciation. 😊👍
Can you please provide the last summary shot of the video, with all methods on one page? Advertising new other videos are actually hindering the view of it. Excellent explanations, by the way, thank you.
Well, one can expect to get a deeper understanding about guitar than machine learning seeing this :P Imo, a complete explaination of these would require one hour per type of model
Machine learning aids environmental monitoring by improving data processing, allowing for more accurate predictions and understanding of climate change consequences and natural disasters.
![[#2024MAMA] ROSÉ (로제), Bruno Mars - APT. | Mnet 241122 방송](http://i.ytimg.com/vi/dgGqD28J6aQ/mqdefault.jpg)
please half the volume of the background music in future videos! good content though, thumbs up!
Yes, for sure, thanks for the feedback, means a lot!
No. Get rid of the music entirely. It is very distracting. There is no need for music if you have something worth saying.
Music is good just lower is better. Really good reference video by the way
Good
Good
Learned more in this 5 minute video than I have in the past two months of watching other videos. Thanks so much for your help
Hi Katie, thanks for your love, support and appreciation ❤️👍
I’ll try my best and share more such quality videos with you!
He has expainened all branches of machine learning ......that is good for biginers like me. To understand ml..
Only few thousands sees this video and I found this is the most brief and easiest to understand the basics of ml model. Thank you.
Glad it was helpful! :)
1.1 M views)
I'm taking a machine learning course and this is what I needed to completely understand each method. Great video, concise and easy to follow. Thanks!
Glad it was helpful! All the best with your course :)
From which course you are learning. I also want to learn machine learning but not able to find which course is best for me. Cam you suggest me which course i should take?
What can you do once you know machine learning? I'm still clueless but I'm into A.I and automotive
@@kenconcepts Hello my friend, see, AI & ML are efficiency-based concepts, meaning they let a business remove repetitive business tasks/processes and automate them (to some extent) with the help of technology. This, in long term, is not just efficient, but also cost effective.
But still, after so much development in AI & machine learning field, there are certain areas that they CANNOT add much value to, I'll recommend you to watch this video: th-cam.com/video/BZUHsuE2Rns/w-d-xo.html
Hope this was helpful!
Same here
It may surprise some people, but logistic REGRESSION is in fact a regression model. The output is continuous: it's a probability. Of course you can dichotomize the output and create a classifier. Just like you can dichotomize any score function or regression model output. So the distinction between regression and classification is not so clear cut.
This is what Azure AI 900 course articles says - Note
Despite its name, in machine learning logistic regression is used for classification, not regression. The important point is the logistic nature of the function it produces, which describes an S-shaped curve between a lower and upper value (0.0 and 1.0 when used for binary classification).
I always find it interesting that the statement "logistic regression is a classification method" is repeated so often, despite 'regression' being right there in the name. Like decision trees (CART), random forest and other similar methods, there are both regression and classification versions of the method. In a binary outcome problem, we model the process as flipping a coin that has a probability p of coming up heads (1) and 1-p of coming up tails (0). We can either predict p, a continuous value between 0 and 1, or we can predict the outcome, itself, which is in {0,1}. The former is regression; the latter is classification. Logistic regression predicts that probability p and logistic classification takes that probability and uses a cutoff (sometimes, but not always, 0.5) to predict the outcome. Many times, the probability is more important (for example, lots of the same type of customer -> you do not want to assume all of them are 1's, when p is estimated to be 0.6) and sometimes the outcome is more important (for example, making a decision to approve an application for credit.)
Thanks for the clarification/correction.
Good point. This was one of my qualms with exams like Microsoft's AI-900 certification -- the answer choices fail to account for nuance
Thank you, i had trouble understanding why Logistic regression is under classification
You are correct and the video misinforms about Decision Trees, Random Forest , SVM, and even Neural Networks - all of which have a regression and classification usecase.
thanks for the beautiful explanation!
I love how the explanation is made to everyone with experience or not in this issue. I’m in the second group and now I have a reference to start. Thank you ☺️
Glad it was helpful! Thank you for your love, support and appreciation 👍❤️
This would be a good video for the person who already understands the vocabulary of machine learning and the different aspects of machine learning. I didn't really gain any knowledge from this video since I'm starting from the beginning of ML.
Been trying to fully figure it all out for a while and here you were concisely explaining the key pointers in exactly 5 mins. Thanks for your help & keep on with the good job mate !
Glad it helped you, my friend!
It was an amazing refresher for me.. Now I know where I need to concentrate more and learn more.
Glad it was helpful!
Thank you, I really needed an overview. Now I have a container to put the information in as I learn it.
Happy to help Kenn! 👍😄
Thank you, my class was s bit overwhelming and this helps to distinguish the stuff more
I'm happy that it was helpful to you, I'll try my best to upload more good videos to help you understand many more concepts!
The summarising ML model is really good. It is very helpful.Thank you sir.
Thanks for your love, support and appreciation ❤️👍
I’ll try my best and share more such quality videos with you!
I find that you glossed over the details of the more difficult models. But provided examples and more depth for the simpler models. For individuals learning ML for the first time, there is a need for people to understand the more complex models in depth. I suggest adding deep dives into each specific model.
I was passed out just by thinking about my ML exam and this video boosted up my confidence I mean at least now I’ve an idea about that subject. Thanks to you
Happy to help! 😄👍❤️
Exam? Grad school?
Interesting how many people in the comments call Logistic Regression a regression model... Logistic Regression outputs a category, not a continuous value. To understand deeper:
Logistic Regression = Linear Regression + Sigmoid (or SoftMax for multi-class) + Unit Step function
Thus, for the binary case, imagine the prediction of the linear regression (a continuous value from -infinity to +infinity) that is than squeezed into the range of 0 to 1, which is not a straightforward probability, but we can interpret it that way. Lastly, a unit step function is applied (the threshold), which makes the prediction categorical.
So, while part of it outputs continuous values, the final outputs is categorical and Logistic Regression is always used as a classification model in the literature.
Great ! It gives an overview of the subject and acts as a roadmap to dive deeper into the study of ML
I want to sincerely thank you for your kind words and appreciation 👍❤️
Great compilation. Very well presented. Clear explanation. One of the very few videos on YT that sums it all so well. It would have taken a lot of effort but worth it, benefiting so many, thanks!
Glad you liked it! ❤️👍
After seeing this video i got a clear idea about all the models thank you😀
Happy to help! 😄
Thanks for explaining all the learning modes of machine learning.
A pleasure indeed to be of help 🙂
The explanation is simple and easy to understand. Thankyou.
Glad it was helpful!
You can also get multi-class classification where the output is more then 2, also you can use neural networks for classification also.
Thanks bro this helps alot, will be watching it multiple times until my brain can sponge it in.
Great primer on ML Models! I would suggest slowing down when you talk and also do a FINAL slide showing all the subcategories you covered under each Supervised and unsupervised models. I would also use real world examples of where each model is being used and applied today.
Done David, thanks for the feedback, I'll account this when creating videos from now on
Nice overview. I think you were super excited. The speed of your chat shows your deep (no pun intended) understanding of the material!
no need to slow down, just change video speed. that's what technology is for
great high-level framework for how to bucket different ML methods
Glad it helped!
this video is very helpful for interview purposes.
Thank you Surabhi for your appreciation ❤️👍
Really nice summary, thanks for putting this together.
I'm happy that it is helpful ☺️👍!!
Amazing content, straight to the point whilst still being detailed
Thanks for explaining machine learning models with such precision, can’t believe it was so short... I can now decide and lead my team on best ml model to select!
Happy to help! I would try to serve the same precision in my future videos. :)
lol
@@venkatsusheelg9658 was here to make the same comment lol
i needed this straight forward video for a very long time thank you so much :)
A pleasure to be of help Shubham, would try my best to upload more such quality videos! 👍
great video. Highly underrated channel!
Thanks for your Kind words Kiran! 👍😄
nice video, straightforward and comprehensive
Thanks for your love, support and appreciation, my friend 👍❤️
Great summary
As a visual person, it would have helped if you zoomed out occasionally when jumping topic to topic, so I could see the tree
Hello my friend, Thanks for the feedback, I'll incorporate this in my future uploads. Have a good day ☺️👍❤️
Thank you for the summary of the machine learning. Hope i meet more usage and example video which comes from Machine Learning.
Thanks for your love and appreciation. I will try my best to deliver more value centric videos! 👍❤️
Very well edited man and the explanation was great!
Glad it was helpful, buddy!
Just the info I needed. Thanks!
Glad it was helpful!
This is awesome. Package your stuff into a Udemy teaching course that rewards you for all this shared knowledge and wisdom about ML!
Wow, thanks for kind words! I'm trying to create a course Peter, trying even harder to launch it soon. Once I have it live, I'll make sure to keep you posted. Thanks again for the appreciation. 😊👍
No
@@learnwithwhiteboard Hi there, have you created a course yet? i would like to buy one from you.
Kind regards
Thank you u made it simple to understand.
Thank you for your love, support and appreciation. I'll try my best and share more such quality videos with you. Cheers! ❤️👍
Thank you this saved my life
Glad it was helpful Kexin! ❤️👍
Really liked this video. Thanks very much!
Glad it was helpful, buddy!
Fantastic and concise summary.
I'm happy that you liked my work ❤️😃
I like the explanation of MLDL, thanks
You are welcome, my friend!
Ty, this helped me alot in my report!
Glad it was helpful! I'll try and share more such valuable videos with you.
Thanks for making it so concise ! Top.
Thank you for your love, support and appreciation. I'll try my best and share more such quality videos with you. Cheers! ❤️👍
Very helpful. Thank you for making this!
A real pleasure Thomas, and thank you for your appreciation my friend! ❤️👍
For sure thanks for making quality educational content!
Short but excellent presentation
Great stuff. Thanks for the overview video. Background music is much too loud tho.
It was very helpful. Thank you.
Glad it was helpful, buddy!
Muchas gracias. Video muy ilustrativo, concreto y preciso para tener un panorama de los modelos de aprendizaje automático (ML)
El placer es mío señor 👍😊❤️
Excellent job 👏
Very helpful to see overall view of all the models
Thanks Uday for your love, support and appreciation. I’ll try my best and share more such quality videos! ❤️👍
Thanks for posting this video. Your explanations make it really easy to get a high-level understanding
Glad it was helpful! 🙏❤️
Very informative to starters
Glad it was helpful! ❤️ 👍
Best video on this topic
Great overview. Thank you very much.
It's a pleasure Denis
Glad to be of help ☺️
Awesome!!! Truly Outstanding content, Thank you.
Glad it was helpful! I'll try my best and publish more such quality videos.
thank you it's really good explaining
Glad it was helpful!
Can you please provide the last summary shot of the video, with all methods on one page? Advertising new other videos are actually hindering the view of it. Excellent explanations, by the way, thank you.
thank you. Very easily explained. Brief and simple.
Glad you liked it Faaiz :)
Liked !Subscribed ! Shared ! Request more clearcut videos like this !
Sure Bhavna, will try to upload more quality videos like this and help people like to learn better & learn faster... Thanks for your support!
@@learnwithwhiteboard :)
Good job. Smart devs should never forget about the newbs.
Super refresher, well done
Thanks Julien for your kind support, love and appreciation ❤️👍
Great intro for the beginners.
great explanation, congratulations
Thanks Rodrigo for your kind words and appreciation ❤️👍
Good overview. Thank you for sharing
very good, excellent description
Thank you for some useful videos
Glad you like them! I'll try and share more such valuable videos with you.
Thanks for all your love, support, and appreciation ❤️👍
Bundle of thanks for this
Glad it was helpful Kexin! ❤️👍
Wow, excellent and to the point. Great work
Thanks Khaled for your love, support and appreciation ❤️👍
Very well explained!
That was a really nice summary!
Glad to hear it! I'll try to publish more insightful videos like this one. Thanks for love & appreciation :)
Great overview. Thanks
Very well explained! look forward to more such videos...
Hi Priya, thanks for your kind words & appreciation ❤️👍, will try my best and produce more such quality videos. Have a great day!
Thanks a lot for this awesome video❤️❤️
My pleasure Krishanu 😊 I'll try and share more valuable videos like this. Thanks for you support, love and appreciation! ❤️
Thank you. it was awesome
Glad you liked it!
This is a very informative video! Well done !
Glad it helped! Thanks for your love, support, and appreciation! 👍❤️
Wow, this is so so good
Thanks Jonathan for your love, support and appreciation … I’ll try my best and continue to share more such quality videos ❤️👍
I wish you the best luck!
Thank you Lucas 🙏❤️
Thank you for your video
Its a pleasure to be of help to you ❤️👍
Well, one can expect to get a deeper understanding about guitar than machine learning seeing this :P
Imo, a complete explaination of these would require one hour per type of model
this is really good, thank you
Very good overview
Great video, very useful for the machine learning library I plan on making :)
Great video! Keep up!
Thanks, will do! ❤️👍
thanks man appreciate it!
Well done. Thank you.🙏
Its a pleasure my friend! I'll try my best and share more such quality videos 😊
Excellent
Glad it was helpful, buddy!
Found short and sweet video 🥰
Glad you found it helpful Vidya ❤️👍
good job done i learned quite well
Thanks Hasan for your love, support and appreciation ❤️👍
Machine learning aids environmental monitoring by improving data processing, allowing for more accurate predictions and understanding of climate change consequences and natural disasters.
Great content!!! brilliant explaination & please get rid off the telemarketing music
Thanks for the appreciation, I have corrected this mistake in my future uploads.
Great work 👍👍
Thanks Harsh for your support and appreciation ❤️👍
this video save my life
Well done
Thank you for your appreciation 👍👍
Thank you
You're welcome
Al is a game changer, already revolutionised many industries, mind blowing 🥷🥷🥷
Strongly agree on this with you 💯
Appreciated 👏👏👍👍👍👌
Thanks for liking 👍❤️
Thanks bro for brushing up the teeth 😊
Welcome 😊
The moment i heard the indian voice i just knew it would be an awesome video :)
Thanks for your sweet words and appreciation, my friend ❤️👍
Good summary. Very helpful !
Thanks Emma for your love and appreciation ❤️👍