amazing video

wow🙂

Probably, one of the best intuitive explainers of why we like to use gradient descent in neural networks, which I ever seen.

Wow! One of the clearest explanations of Bayes Theorem I’ve come across!

this was super helpful

excellent the AI chip can not avoid the principles of the system architecture of the hardware fundaments the rules and algorithm like round robin algorithm, FIFO etc and neurons also as follows the signal process of the data communications as well. here keep in mind binary , qubit and hybrid process. the voting process of blockchain for digital encryption is kind of like similar. Chip has main 3 gates AND Logic Boolean , OR Logic Boolean and Not logic and total combo of 7 gates.Qbit49 is a quantum are Shor's algorithm probability has 3 state also 3 methods quantum tunnelling, entanglement, superposition , binary has yes /no ,Qbit has Yes, No, (yes or no).

❤❤❤❤❤❤

Best Knowledge for real. The video is very helpful. ❤

Great presentation, Brandon. I prefer your simple graphics and pace over the highly distracting, animated videos from other educators.

You will spent hours trying to find the right video, this 26 min clip is all you need.

Great explanation!!

Thanks for such an amaizing video

Very good

thanks

The first one put down is in the wrong spot.

Now in 2024, and I can’t imagine the degree of triggering all these assumption examples would give a certain disturbed minority of the population… Also I guess it’s only because statistics inhabits the furthest recesses of YT land that someone hasn’t called for it’s banning or demonetisation at the very least!

Hi Brandon, when giving it an unseen image, how do you know whether to draw a line from the vote percentage to the x or to the o?

You are not suppose to copy code from vid

What is i_conv: i_conv

It's great. However, the purpose of ReLU is to introduce non-linear functions rather than normalization.

Your PDF version please

I hope you find the below annotated summary of the explained method of "opening the box" helpful😊 In the process of going through the steps of the method, think about the following questions*: q1: What is the "box" design for? (e.g. What is the purpose of SVM?) q2: What is the "box" used for? (e.g. What is SVM used for?) q3: How to visualize the key concepts? (e.g. How to visualize SVM kernel trick?) q4: How the underlying Math works? I'd like to think of the below "steps" as strategies that I can select from and mix together (depending on the box I'm trying to open). Steps: 1. Read the original source that explains the "box" (e.g. scikit-learn docs).** 2. Read good Tutorial(s). 3. Watch good KZfaq videos. 4. Read some good (blog) posts. 5. Explain the "box" to yourself and try to draw illustrations of the key concepts. 6. Choose a toy example (i.e. simple example that preserved the fundamental features of the "box".). 7. Explain it to a 12 year old (to avoid using jargon and to get to the essence of the "box"). 8. Understand the weaknesses of the box. (e.g. What conditions make SVM a poor method of choice?) So, that's it! This is how you open a box 🙂 Footnotes: * Of course some of the questions are not applicable to some "boxes" :) ** Be aware that this step might not be accessible to beginners.

Loved the analogies with real life philosophies, brilliant!

Nice explanation of how Machines Learn via Neural Networks. However, a downside of this video is that it is still teaching subconsciously that white is good and black is bad and all the racial connotations that go with that! It would have been so much better if the chosen colours had been say any colour that has no ties to race - say blue and green! I know I'll be lambasted for this but it is how I feel whether and nothing changes that...

That's a masterpiece, not only have I learned how in detail convolutional neural networks work, but also I've learned how I should explain hard subjects to others. Thank you.

3:33 why did -1.075 become positive?

very good explain. thanks :)

Very very rare way to explain a neural network in such a great depth. Loved the way you explained it ❤

the depth of the explanation and visualization, there is no word to describe how much it express and help to grasp the most fundamental and core concept of Neural Networks. THANKS Bra

NO CREO Q FUNCIONE

Just awesome @brandon I do have a question though, input image of 9x9 and filter of 3x3, how did we end up with feature map of 9x9 ? Shouldnt it be smaller than 9x9

Nice. Very nice actualy But I can think of 2 questions having an answer to which in this video would make the video from very nice to perfect. 1) In 1D, 2d, or 3d cases, is the process of fitting the separating line (or plane) iterative while some loss is being calculated just like in Neural networks? Or it is more like in Linear Regression where I can fit the line iteratively though, but there is no need to do it since there is a straightforward formula to find the slope and the intercept of the best-fitted line. 2) What is the advantage of the observation space being bent instead of bending the "cutting plane"? Thank you very much

What a diamond of a channel i just found ... incredible!

I had a diffi ultrasound time understanding the convolution layer, this course is the best among all courses I saw on KZfaq, keep the good work, you saved me , I was struggling understanding and now I'm completely clear. Thanks alot

insanely good explanation, never seen anything like this. thanks a lot

How do you calculate the partial derivative of the loss in regards to the output?

Hello, I have a project on building a Deep k-Nearest Neighbors (DkNN) model for image recognition. Can you guide me on the steps needed to build the model?thank you!

Respect Sir, Thank you so much- I am more than satisfied with your lecture.

its clear till 17:57 , but i just lost it at 18:01, just didnt understand why each lines there changed from 1.0 to -0.2 , 0.0 , 0.8 , -0.5.......can someone explain ?

Hot damn this video is soo goood

The way you explain is amazing! And visually seeing the convolution step by step was just brilliant! Thank you so much! ❤

Nice video, the best one I've seen yet about the concept of partial autocorrelation!

Bonjour Q1 : At 5:42. Where the .96 comes from? The square "says" P(woman==0.2 , P(man) = .98. Should we read P(man AND long) = P(man) * P(man | long) = 0.98 * 0.04 = 0.04 Q2 : At 17:00 I understand the mean of the normal distribution in the back is 17. OK, but what is the standard deviation. Is it equal to the one calculated with the 3 values (13.9, 17.5, 14.1) , do we use the standard error or something else? This is not yet clear for me. Merci

Its not working,, any other options

This channel is a goldmine ty

не могу слушать это "хвайт"

Hi, Thank You so much. I want to be a Data Scientist. How do I go through your playlist. Can you please help me what to do first -last ?

The ice tea part killed me 🤣🤣

I wonder what he thought about the probability of talking snakes.

Within the first 10minutes when you explain 'convolution', aren't you TRYING to explain 'cross correlation'? I say 'trying' because it doesn't look like 'cross correlation' either since you averaged the result of the summation. So technically, what you just explained within that time frame is a cross correlation step, after which you implicitly applied a box averaging filter. Correct me if I'm wrong.