Gradient Descent - Simply Explained! ML for beginners with Code Example!

preview_player
Показать описание
In this video, we will talk about Gradient Descent and how we can use it to update the weights and bias of our AI model. We will learn how to minimize the average loss of our model, and get a warm introduction to "epochs" and "learning rate"!
We will of course also see a working example of the math behind Gradient Descent, and learn how to implement it with code by using our superior Python skills! 🐍🐍🐍
Before we dive in, make sure you are proficient with the previous topics of my AI series - Perceptron, Weights, Input, Weighted Sum, Target, Prediction, Activation Function, Loss Function & Cross-Entropy Loss.
If you are 🆕 new 🆕 to these concepts, please watch my other tutorials first (links below):

🛑✋ HAVE YOU WATCHED? ✋🛑

⭐ My Cross-Entropy Loss Tutorial ⭐:

⭐ My Perceptron Tutorial ⭐

⭐ My Introduction to ML Tutorial ⭐

*****************************************
⭐ time stamps ⭐
*****************************************
00:00 - what is gradient descent?
00:37 - gradient descent vs perception
01:04 - sigmoid activation function
01:45 - bias and threshold
02:06 - weighted sum - working example
02:37 - sigmoid - working example
03:03 - loss function - working example
03:32 - how to update weights
04:17 - what is learn rate?
05:06 - how to update bias
05:37 - gradient descent - working example
07:13 - what is epoch?
07:38 - average loss per epoch
08:37 - gradient descent code example
12:13 - thank you for watching! stay in touch!

*****************************************
⭐⭐⭐ Get Starter And Complete Code (UPDATED FEB 2023) ⭐⭐⭐
*****************************************

Thank you! 🤩
Рекомендации по теме
Комментарии
Автор

Hi Maria, first of all thank you for everything🙂
I tried to open the links to the codes and failed
I would love to receive an active link

נתיקרסנטי
Автор

You made it easy... I was learning this from books it took me 4 days to understand... You explained in 10 mins... I can understand your hard work 😊😊😊

abhishekgaikwad
Автор

I have been in ML for 6 years and that was one of the best explanations for Gradient Descent. I wish someone explained the way you explained it when I first started, amazing work!

larrybird
Автор

Maria has an elegantly simple and yet powerful style of delivery of complex matters that I’ve not seen anywhere else. It is a truly unique way of educating.. it’s a marvel

CrypticPulsar
Автор

Your videos are more and more professional and you explain with so much detail that it's impossible not to learn. Thank you so much for sharing your knowledge with us!

mschon
Автор

You are the best teacher no teacher I have ever had :)

DanielHernandez-hltn
Автор

I want to thank you so much as you helped me a lot from knowing nothing in machine learning to actually making an ML project for my graduation and making me realise that I want to pursue it as my future😄

harshitsrivastava
Автор

Top level
Best channel, best instructor
Best material, amazing editing.

This channel should hit 1m
before 2022.

Bloody cross entropy finally smile to me after weeks of reading

shaharrefaelshoshany
Автор

I have wanted to know how ML works for ages - you have got me started. Thank you.

valueengines
Автор

You can present complex issues in a very simple and clear way, thank you so much! Greetings from Poland :D

dariusztomaszewski
Автор

Best explanation of GD in 12:34 mins. Perfection!

gabeblanco
Автор

this IS actually the best explanation. ive watched like 30 even from MIT videos

sugaith
Автор

WOW, I am so very glad that I started with this video rather than the materials you mentioned. It may take several replays for full understanding but I already get the idea & concept behind Gradient Descent, thanks to your awesome tutorial. I am super excited to learn more from your coming episodes.

digigoliath
Автор

explanation without derivative) it's brilliant) better than in university

dicloniusN
Автор

Excellent Explanation with good catching examples and presentation 🤟

dr.aravindacvnmamit
Автор

Mariya, I follow a lot of your wisdom and knowledge pills with the hope to get better at ML and AI. You're a phantastic teacher,
very clear, consequential, and also beautifull to look at with all your necklaces. You cannot improve your teaching skills as you are already at the top. Though, one thing can be improved: the naming and classification of all your materials. Every time I am looking for a pill that I saw in the paste, it takes me a lot of time to find it again, even with the search abilities of youtube. That is the only issue I kindly suggest you to rethink. The rest is awsome. Thank you for your attention.

alessandrocagnola
Автор

You are freaking awesome!!! And I teach this stuff!

datasciencedoctor
Автор

Thanks! Never saw an explanation which was as conprehensible as yours

serenmuratdagi
Автор

wow! Maria, you are a star and my favorite vlogger. Keep up the good work! thanks!

benrav
Автор

Leaving a comment to help with the algorithm.

JessWLStuart