วีดีโอ

You're welcome

You’re welcome!

Thank you! I’ll look into it.

If you want, you can still change the background of each short to be different. It won’t take too long to manually remove and add a new background to each short, and you would still save a lot of time by automating the other processes.

If you want to add sound to each video, you have to add sound to one video, align it and then manually duplicate it until all videos have sound. I have not yet found a more automated approach. If I find one, I’ll let you know!

Hey, I am not an expert but I just checked your channel. It looks great. People might not be clicking on the videos because they look like ads, they are all less than 5 minutes. That was my first impression. I dont know much though I just started a TH-cam channel.

Yes of course

Thank You@@TheAIGuyExplains

You're welcome

You're welcome

Thank you so much for your thoughtful feedback! I really appreciate your positive comments and I'm glad the video was helpful. Your suggestion about providing a quick reminder about the matrix X is valuable, and I'll definitely keep that in mind for future videos. Thanks again for watching and taking the time to share your thoughts!

Thank you

Thank you!

Thank you!

Thank you!

Hi there! I appreciate your enthusiasm for diving into the world of neural networks and backpropagation. I'm currently working on a comprehensive video series about machine learning, starting from the basics. I recommend checking out all the videos starting from 1.1, where I discuss the regression problem. Right now, I'm focusing on explaining linear regression, which forms the foundation of machine learning. Understanding linear regression and logistic regression is crucial before delving into neural networks. After covering these fundamentals, I'll be diving deep into the intricacies of neural networks in the upcoming videos. So I recommend that you start from 1.1 and work your way up to the most recent video! Then once you saw all these video's, you'll have a good understanding about linear- and logistic regression and in a little over a month, I will start on Neural networks.

Thank you

Thank you! I totally agree with you, that’s why the video’s after that are without background music

Thank you!

You're Welcome!

Thank you

Indeed, Neural networks are amazing

Thank you

Thank you for sharing your feedback with us. We genuinely appreciate your input. We have ceased the use of background music in the linear regression series starting from 1.3 gradient descent onwards. We hope this adjustment enhances your learning experience.

Thank you!

Thank you!

You’re welcome!

You're welcome!

Thank you!

Great observation! You're absolutely right. In the context of linear regression, especially in the multidimensional case, closed-form solutions like the normal equation involving matrix inversion can indeed be used to find the exact minimum. However, as you rightly pointed out, the computational cost of inverting matrices, especially for large datasets, can make gradient descent a more efficient choice and this is something I will explain after I made a video about linear regression with multiple features. Additionally, your insight about the variability of the minimum due to different sets of data points is indeed something I can explain in one of the next videos. Thanks for adding this valuable perspective to the discussion and I shall explain both in the upcoming videos!

Looking forward to the next ones!

I just uploaded the video explaining the normal equation method. I would appreciate your feedback on the clarity of the explanation. Are there any areas that you think need further clarification or improvement?

@@TheAIGuyExplains Thanks for keeping me posted... i'll comment on that video!

thank you!

You're welcome

Thank you!

Thank you!

Absolutely, that comparison is quite on point! At its core, machine learning does heavily rely on statistical methods, leveraging data for decision-making. The analogy of machine learning being "statistics on steroids" is quite fitting. With the surge in computational power, machine learning takes statistical analysis to new heights by not just analyzing data but also allowing systems to learn, adapt, and make predictions or decisions without explicit programming. It's like statistics empowered by technological advancements, enabling machines to handle more complex tasks and vast amounts of data efficiently. In many ways, machine learning amplifies the capabilities of statistics, providing solutions and insights beyond what traditional statistical methods could achieve. It's a fascinating evolution in the realm of data analysis and decision-making.

​@@TheAIGuyExplains Statistics started studying parametric models in part due to a necessity of reducing calculations (for example, modelling the height of a population using a gaussian distribution allows us to say things about the number of people with certain height, or even to distinguish between populations. Such model only require us to calculate two parameters). But as we increased our computational power, we could use more advanced models to the current point in which we can use billions of parameters... In a way, machine learning is the natural evolution of statistics. We are still exploring the limits of the machine learning approach... will we be able to get an Artificial General Intelligence (AGI) by just creating bigger models? will we be able to define what an AGI is? It seems like each time we achieve a milestone in artificial intelligence, we move the goal of AGI even further (In the 60s a machine able to beat humans at chess or go would have been considered intelligent... we thought that a machine able to create art would be intelligent... we also thought that a machine able to hold a coherent conversation would be intelligent...)... It is an exciting time to be a live! (though, to be fair, it is always an exciting time to be alive)

thank you

thank you

I agree

Thank you!

You're welcome!