I'm starting to get in to it but I think you need to have some background in data science, math (not 100% required, but linear algebra is most important, but also Calculus is useful), and coding (Python is probably the best for machine learning, (which is computationally slower than things like C, but built for data science))
This is just awesome, I was trying to learn ml models since 2-3 months but getting confused, this one video made me understand each with clarity in just 1 hour😮, this is awesome ❤
I'm preparing a class about algorithms for high school students and this video has synthesized and simplified like half of the job. I'll have to give you credit in the references section. Great job!
You just covered the first month of my 400 level machine learning class, minus the math, examples, and a a couple newer dimension reduction techniques. This video is a good resource.
This was extremely useful, thank you. If anyone is learning deep learning, this is a great place to start. Every deep learning book/course should open with an overview of the algorithms (would have saved me a lot of confusion).
As someone who knows and uses all algorithms, I will store this video to rewatch from times to times, just to not forget about solutions, I might not using that much. Well explained for a brief overview.
Thanks for this guideline. It makes me want to actually take a class on data science and information theory. I've been putting off learning about them for so long since I figured I could just theorized them from fundamental by tracing math knowledge. But, reality is that I can only do so much to reinvent the wheel when I don't know the existing wheels out there.
I would add the distinction between relationship based and data driven models. Relationship-based statistical models rely on predefined hypotheses and the relationships between variables. Once a hypothesis is confirmed, additional data is not necessary for validation. On the other hand, data-driven machine learning models continuously learn and improve from the data, identifying patterns without the need for predefined hypotheses.
Love the animations and simplicity you explained all the topics. Could you take more time to upload more such videos but with complete lectures on each topic. Everybody will love that.
00:03 Overview of major machine learning algorithms 01:52 Supervised learning involves predicting and classifying data 03:41 Machine learning algorithms explained in 17 min 05:31 Understanding the importance of hyperparameters in machine learning algorithms 07:16 Kernel functions allow for the efficient creation of nonlinear decision boundaries. 09:07 Ensemble algorithms combine multiple decision trees to create powerful models. 10:50 Machine learning algorithms are designed to design complex features implicitly 12:34 Introduction to Unsupervised Learning and Clustering 14:21 Dimensionality Reduction in Machine Learning 16:10 Common machine learning algorithms explained
Very great ! Would be also very interesting to combine it with type of deep learning models, like CNN, RNN, encoder/decoder, LMM etc, and in which use case you use them with limitations :) , I think I haven't seen yet these kind of deep learning overwiew.
very unique and my one of the faviorite video cause im looking for it for a long time and please make video on how to select regression models and classfication models like some patternor or trick to choose appropriate models thank you good video
i have a question what type of algo will be used if someone wants to create a model that helps marts(as Walmart type of stores) to predict what type of product should they buy more using historical data of the store, notify the management of the stocks that are low. also in this type of problem should they use both classification and regression algo?
No, large k is underfit, small k is overfit. Imagine you ahve 500 samples and k is 1000, you will always predict the same thing, the majority class, so its clearly underfit. If k=1 you will always predict the same as the point closest to you so it's clearly highly dependent on your training data (overfit)
Don’t forget to like and subscribe!* *Doing so requires you to locate and navigate to the “like” and “subscribe” buttons respectively, which is (literally) beyond the scope of this video.
![Chris Langan's CTMU: Introduction To The Human Singularity [Using AI to Defeat The Tech Singularity]](http://i.ytimg.com/vi/c3GBFiW2bC4/mqdefault.jpg)
Wow! I've taken many machine learning courses to date, but his breakdown is spot on! So concise! 🎉👍 Great job. Do you have more?!
Amazing! As someone who wants to learn ML but has little to no idea about it yet, this video was really easy to follow. Keep it up!
I'm starting to get in to it but I think you need to have some background in data science, math (not 100% required, but linear algebra is most important, but also Calculus is useful), and coding (Python is probably the best for machine learning, (which is computationally slower than things like C, but built for data science))
Love and respect from a small village in India i even can't have this type of valuable info from the paid sources Thanks you so much🥰
Keep it up king! You got this!
Any idea where I can learn all stats and regression shown in the video@@bananasmileclub5528
Dude WHAT? I spent a week trying to understand all of these and here I am, understood everything crystal clear in an hour 🤨
Just took my 5 month long intro to ML course in 17 minutes! Nice.
Dude, you just made my concepts so clear in just 17 minutes. Now I know what to use for my application. Thank you very much! You are Amazing!!!
This is just awesome, I was trying to learn ml models since 2-3 months but getting confused, this one video made me understand each with clarity in just 1 hour😮, this is awesome ❤
I'm preparing a class about algorithms for high school students and this video has synthesized and simplified like half of the job. I'll have to give you credit in the references section. Great job!
Learning Machine Learning is amazing with this video
You just covered the first month of my 400 level machine learning class, minus the math, examples, and a a couple newer dimension reduction techniques. This video is a good resource.
He just showed PCA lol
Please please more computer science content like this!!! ❤️
I am happy to realize that I already used all of those and played with the implementation of half of them in the doctorate.
Studying for my midterm next week. This was a great quick overview!
these short visualized explanations help way more than a certain online course im currently taking 😭👍
this is a great summary for ML learners
Awesome sir. Many thanks. - Nepali from USA
TH-cam recommend this channel as No Fluff channel,
Finally, an amazing video that is not clickbait
Every second of this video is beyond the scope of this video 😅
The best video among others on the subject I've been passing through. Thank you
This was extremely useful, thank you. If anyone is learning deep learning, this is a great place to start. Every deep learning book/course should open with an overview of the algorithms (would have saved me a lot of confusion).
As someone who knows and uses all algorithms, I will store this video to rewatch from times to times, just to not forget about solutions, I might not using that much. Well explained for a brief overview.
Thanks for this guideline. It makes me want to actually take a class on data science and information theory.
I've been putting off learning about them for so long since I figured I could just theorized them from fundamental by tracing math knowledge.
But, reality is that I can only do so much to reinvent the wheel when I don't know the existing wheels out there.
Great explanation! Time to dive into them one by one
top video! make a part 2 with more advanced algorithms like sarimax etc
I recommend this video. Not only a time saver, but quite a good description of what these methods do and when they work best 🎉
I would add the distinction between relationship based and data driven models.
Relationship-based statistical models rely on predefined hypotheses and the relationships between variables. Once a hypothesis is confirmed, additional data is not necessary for validation.
On the other hand, data-driven machine learning models continuously learn and improve from the data, identifying patterns without the need for predefined hypotheses.
It's very interesting and easy to understand, we need real time example with code in seperate topics
My whole semester material in one video. I love it!!! 🎉
Excellent overview
Great video, thanks for making this. At the end however, I’m unable to see the last two slides due to cards covering it.
This was awesome!
Love the animations and simplicity you explained all the topics.
Could you take more time to upload more such videos but with complete lectures on each topic. Everybody will love that.
Man, I love this video. Thank you so much for this video, now I'm confident about learning machine learning.
Great video, but I think you left out one important unsupervised learning, the Self-Organizing Map, (SOM)
Thank you; it was super helpful for me to understand the big picture of ML!
Great explained and good to remember some algorithms in the future
00:03 Overview of major machine learning algorithms
01:52 Supervised learning involves predicting and classifying data
03:41 Machine learning algorithms explained in 17 min
05:31 Understanding the importance of hyperparameters in machine learning algorithms
07:16 Kernel functions allow for the efficient creation of nonlinear decision boundaries.
09:07 Ensemble algorithms combine multiple decision trees to create powerful models.
10:50 Machine learning algorithms are designed to design complex features implicitly
12:34 Introduction to Unsupervised Learning and Clustering
14:21 Dimensionality Reduction in Machine Learning
16:10 Common machine learning algorithms explained
pls make a more indepth video on this topic or realise a course on data science and machine learning we want to learn from you
a gem in youtube
All a.i concepts in 10 mins plz .like iceberg
Wonderful, Nice video! 10 years in business.
What do you consider is the best paying skill in a Data Scientist? 😊.
never understood how machine learning works till now
Very great ! Would be also very interesting to combine it with type of deep learning models, like CNN, RNN, encoder/decoder, LMM etc, and in which use case you use them with limitations :) , I think I haven't seen yet these kind of deep learning overwiew.
Now this...this is good content. Keep it up. You earned a subscriber!
Wonderful video. Thank you so much for taking the time to create this.
Man you did a great jon
very unique and my one of the faviorite video cause im looking for it for a long time and please make video on how to select regression models and classfication models like some patternor or trick to choose appropriate models thank you good video
Wonderful, waiting for more content like this
Now do the 10-part-14-hour-long videos on MatLAB, Python, and R
this video is great and deserves the thumbs up
This is an amazing introduction!!
Sir, this was soo helpful and easy to understand. Thanks a lot for sharing
8:15 great example
Informative.
What algorithm do you use when the features are tokens and the predicted object is a category?
I know some statisticians that would be triggered by you called these methods machine learning, but nice vid
Excellent video!, Thank you!
great explanation
It's so clear
this road map was great
successfully observation to learn them
Awesome video, thanks
Very helpful, thanks 🙂
which one is most useful and better to learn for future?
now I understood non-linearity
Nice explanation, Thank you!
Great Video! An update with gaussian processes would be cool. They are non conventional, and not so famous, but part of the neighborhood 😅
You can always add extra to videos like this one, but this is good enough to give you a taster.
great content. thank you so much!
Great content.
Great Job bro
Awesome video!
I use Optuna for selecting my algo.
was a very great video thanks
Awesome, thanks!!
Instant subscribe on my part.
Lookingror this type of vid
Very useful!
Thank you so much for this! easy to understand 👍
Thanks sir !
Thanks ❤
Which algorithm is incremental and continuous?
good video
Great 👍
very interesting!
You are amazing
Bro thought we wouldnt notice @8:13
Hehe yeah I had a giggle
it was a very relevant example thou!
thanks
Good vid
Do you think autoencoders should've been a part of this video?
Self-organizing maps?
Any book recommendations for novice?
I really liked what I mentioned in my other video (th-cam.com/video/jwTaBztqTZ0/w-d-xo.html&ab_channel=InfiniteCodes):
www.statlearning.com/
we need more videos if we want to understand better how AI works
i have a question what type of algo will be used if someone wants to create a model that helps marts(as Walmart type of stores) to predict what type of product should they buy more using historical data of the store, notify the management of the stocks that are low. also in this type of problem should they use both classification and regression algo?
Now I can mention in the resume, ML Expert 😅
6:03 isn’t the opposite? with k=1 we have underfitting and with k=1000 we have overfitting
No, large k is underfit, small k is overfit.
Imagine you ahve 500 samples and k is 1000, you will always predict the same thing, the majority class, so its clearly underfit. If k=1 you will always predict the same as the point closest to you so it's clearly highly dependent on your training data (overfit)
Brvh please more videos😅😢
Radial Basis Function NN?
Sehr gut
Don’t forget to like and subscribe!*
*Doing so requires you to locate and navigate to the “like” and “subscribe” buttons respectively, which is (literally) beyond the scope of this video.