I think it's a great benefit to humanity to have this course publicly available. What an amazing resource! This definitely will get a lot of people involved in AI / ML who maybe never would have learned it otherwise. Super awesome!
@@stanfordonline really thank you guys, it helps people from backyards of the world to gain reasonable knwoledge which can be applied to get a real job and change thier lives
By uploading such a pedagogical resource for free, you are enabling every human on earth with internet access to create fantastic ML tools that would otherwise be impossible due to the high cost of top-notch education. Thus, you are setting the bar for human creation higher and higher. Thank you!
Here is the table of contents of this lecture (generated by podsqueeze) The Introduction [00:00:04] Introduction of the teacher and their background in machine learning, as well as their involvement in building machine learning products. Logistics and Course Structure [00:02:00] Discussion of the teaching team, including the course coordinator and TAs, and an overview of the course structure and logistics. Prerequisites and Course Goals [00:04:13] Explanation of the prerequisite knowledge needed for the course, including probability, linear algebra, and programming, and the goals of the course in providing foundational knowledge in machine learning. Lecture Overview [00:11:33] The teacher provides an overview of the course, including project criteria, topics, homework, and lectures. Discussion Sessions [00:17:08] The teacher explains the optional discussion sessions led by TAs and the flexibility in choosing which session to attend. Definition of Machine Learning [00:18:49] The teacher discusses historical definitions of machine learning by Arthur Samuel and Tom Mitchell, emphasizing the ability to learn without explicit programming and the importance of experience, performance measures, and tasks. Supervised Learning [00:25:52] Introduction to supervised learning and the concept of using a dataset to predict an output based on input features. Regression and Classification Problems [00:34:04] Explanation of regression problems (continuous variable prediction) and classification problems (discrete variable prediction). Applications of Machine Learning [00:36:11] Overview of broader applications of machine learning that will not be covered in the course. Image Classification [00:37:28] Describes the task of image classification and the importance of the ImageNet dataset in deep learning. Object Localization [00:38:45] Explains the concept of object localization in computer vision and how bounding boxes are used to represent objects. Language Applications [00:39:52] Discusses language problems in natural language processing, such as machine translation, and the complexity of the y variable in these applications. Introduction to Topic Modeling [00:50:40] The teacher explains the concept of topic modeling and how it can be used to identify topics in a dataset. Applications of Topic Modeling in Social Science [00:51:49] The teacher discusses how topic modeling is used in social science research to analyze large amounts of text data, such as blog posts, to understand trends and patterns. Word Embeddings and Semantic Similarity [00:54:02] The teacher explains the concept of word embeddings and how they capture the semantic meanings of words, as well as the relationships between words. Concerns about numerical problems in the training corpus [01:03:46] Discussion about whether all multiplication problems are included in the corpus and how the model learns from basic information. Ensuring the accuracy of training corpus [01:05:06] Exploration of how to prevent wrong information from being included in the training corpus and the possibility of adversarial poisoning. Introduction to reinforcement learning [01:07:50] Explanation of the difference between making predictions and making decisions, and the concept of reinforcement learning for sequential decision-making tasks. Deep Learning Basics [01:15:23] Explanation of deep learning as a technique that can be used in various machine learning tasks and its significant impact on the field. Learning Theory and Algorithm Decisions [01:16:32] Discussion on the trade-offs and decisions involved in training machine learning algorithms, including feature selection and minimizing test errors. Guest Lecture on Robustness and Fairness [01:17:53] Introduction to the societal impact of machine learning and the importance of addressing issues of fairness and robustness in machine learning models.
Thank you Stanford. It is amazing to see your commitment make our world better by sharing courses for free. Specially considering you are giving the opportunity to learn and a pottential better future to so many people far away / without resources that would never have the chance to learn such things otherwise.
Thanks!! Stanford for the lectures I've been working understanding machine learning and neural network from MIT and the Professor Andrew Ng aswell to later move on to work on quantum machine learning with IBM.
Thank you Stanford Community and Key Machine Learning Lecture One Thank you all I want the complete course of machine learning to be done like this and what feedback is given after completing the course feedback how to work how to develop like this is the most urgent need is
It would have been best if there was a specific platform for this machine Learning. They are regular classes, discuss everything, practice regularly and make solutions for the tasks you have on a regular basis. This machine learning course is constantly creating a platform through online. I request you to develop the platform to launch the machine learning or deep learning course. I am Bangladeshi and a student so I am very willing and interested.
Thank you very much Stanford for this valuable course and we all know the value of this course so thank you very much. I have some questions is this course recent and how much time it will take to complete this course
Thanks for your questions! This course was recorded Spring Quarter of 2022. The time to complete this course varies, however graduate students enrolled in this course typically spend 10 weeks, 15-25 hrs/week. Hope this helps!
Well you should follow the most recent one as AI and machine learning evolves really quickly. This one is from 2022, a lot has happened in two years so you can already consider its partially outdated, still its very great content and a unique chance for everyone in the world to get access to that kind of high-level education.
Hi there, thanks for your question and for watching! We will publish one new lecture per day for the next few weeks. The entire course will be available to view before the end of the month (August 2023).
Thanks for your question! Prerequisites for CS229 - Students are expected to have the following background: Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program in Python/NumPy. (CS106A or CS106B, CS106X.) Familiarity with probability theory. (CS 109, MATH151, or STATS 116) Familiarity with multivariable calculus and linear algebra (relevant classes include, but not limited to MATH 51, MATH 104, MATH 113, CS 205, CME 100.) You can find more information on the course website: cs229.stanford.edu/syllabus-spring2022.html
Multivariable calculus: treat other variables as constant when taking derivative/integral. Linear algebra: manipulate matrices and learn about vector spaces and bases. Not much to learn so yes is possible
![🔴 ฟุตบอลแชมป์กีฬา 7HD แชมเปียน คัพ 2024 [รอบรองชนะเลิศ]](http://i.ytimg.com/vi/zPm8ClLVhoE/mqdefault.jpg)
Stanford's dedication to open access education is truly commendable, providing invaluable learning opportunities to countless individuals worldwide.
Thank you for your comment, we love to hear such wonderful feedback!
I think it's a great benefit to humanity to have this course publicly available. What an amazing resource! This definitely will get a lot of people involved in AI / ML who maybe never would have learned it otherwise. Super awesome!
Thank you Stanford for spreading the knowledge across the world.
Thanks so much for your comment and feedback!
@@stanfordonline When will all the lessons be available?
@@franciscojpedrozac3824use to your brain …..they won’t
It’s all about money
@@stanfordonline really thank you guys, it helps people from backyards of the world to gain reasonable knwoledge which can be applied to get a real job and change thier lives
By uploading such a pedagogical resource for free, you are enabling every human on earth with internet access to create fantastic ML tools that would otherwise be impossible due to the high cost of top-notch education. Thus, you are setting the bar for human creation higher and higher. Thank you!
as a passionate of AI from Cameroon and not able to afford for a formal education this course is valuable for me. Thanks so much to tanford
Here is the table of contents of this lecture (generated by podsqueeze)
The Introduction [00:00:04]
Introduction of the teacher and their background in machine learning, as well as their involvement in building machine learning products.
Logistics and Course Structure [00:02:00]
Discussion of the teaching team, including the course coordinator and TAs, and an overview of the course structure and logistics.
Prerequisites and Course Goals [00:04:13]
Explanation of the prerequisite knowledge needed for the course, including probability, linear algebra, and programming, and the goals of the course in providing foundational knowledge in machine learning.
Lecture Overview [00:11:33]
The teacher provides an overview of the course, including project criteria, topics, homework, and lectures.
Discussion Sessions [00:17:08]
The teacher explains the optional discussion sessions led by TAs and the flexibility in choosing which session to attend.
Definition of Machine Learning [00:18:49]
The teacher discusses historical definitions of machine learning by Arthur Samuel and Tom Mitchell, emphasizing the ability to learn without explicit programming and the importance of experience, performance measures, and tasks.
Supervised Learning [00:25:52]
Introduction to supervised learning and the concept of using a dataset to predict an output based on input features.
Regression and Classification Problems [00:34:04]
Explanation of regression problems (continuous variable prediction) and classification problems (discrete variable prediction).
Applications of Machine Learning [00:36:11]
Overview of broader applications of machine learning that will not be covered in the course.
Image Classification [00:37:28]
Describes the task of image classification and the importance of the ImageNet dataset in deep learning.
Object Localization [00:38:45]
Explains the concept of object localization in computer vision and how bounding boxes are used to represent objects.
Language Applications [00:39:52]
Discusses language problems in natural language processing, such as machine translation, and the complexity of the y variable in these applications.
Introduction to Topic Modeling [00:50:40]
The teacher explains the concept of topic modeling and how it can be used to identify topics in a dataset.
Applications of Topic Modeling in Social Science [00:51:49]
The teacher discusses how topic modeling is used in social science research to analyze large amounts of text data, such as blog posts, to understand trends and patterns.
Word Embeddings and Semantic Similarity [00:54:02]
The teacher explains the concept of word embeddings and how they capture the semantic meanings of words, as well as the relationships between words.
Concerns about numerical problems in the training corpus [01:03:46]
Discussion about whether all multiplication problems are included in the corpus and how the model learns from basic information.
Ensuring the accuracy of training corpus [01:05:06]
Exploration of how to prevent wrong information from being included in the training corpus and the possibility of adversarial poisoning.
Introduction to reinforcement learning [01:07:50]
Explanation of the difference between making predictions and making decisions, and the concept of reinforcement learning for sequential decision-making tasks.
Deep Learning Basics [01:15:23]
Explanation of deep learning as a technique that can be used in various machine learning tasks and its significant impact on the field.
Learning Theory and Algorithm Decisions [01:16:32]
Discussion on the trade-offs and decisions involved in training machine learning algorithms, including feature selection and minimizing test errors.
Guest Lecture on Robustness and Fairness [01:17:53]
Introduction to the societal impact of machine learning and the importance of addressing issues of fairness and robustness in machine learning models.
Thank you Stanford. It is amazing to see your commitment make our world better by sharing courses for free. Specially considering you are giving the opportunity to learn and a pottential better future to so many people far away / without resources that would never have the chance to learn such things otherwise.
Thanks so much for watching, and for taking the time to leave us this feedback!
Thanks!! Stanford for the lectures I've been working understanding machine learning and neural network from MIT and the Professor Andrew Ng aswell to later move on to work on quantum machine learning with IBM.
Thank you for keeping updating the courses, Appreciate!
Thank you Stanford for providing this course
Lecture starts from 18:30
thank you stanford for this detailed course on introduction to ML. can someone please tell what should i do next after completing this?
Can't wait to go though the lecture series.😊
very inspiring. great work Stanford!!
Thank you Stanford Community and Key Machine Learning Lecture One Thank you all I want the complete course of machine learning to be done like this and what feedback is given after completing the course feedback how to work how to develop like this is the most urgent need is
Thanks Stanford, this is super helpful!!
Where can we find the problem sets?
Can't wait for this course ❤
It would have been best if there was a specific platform for this machine Learning. They are regular classes, discuss everything, practice regularly and make solutions for the tasks you have on a regular basis. This machine learning course is constantly creating a platform through online. I request you to develop the platform to launch the machine learning or deep learning course. I am Bangladeshi and a student so I am very willing and interested.
Thanks for materials! Highly appreciated
Thank you very much Stanford for this valuable course and we all know the value of this course so thank you very much. I have some questions is this course recent and how much time it will take to complete this course
Thanks for your questions! This course was recorded Spring Quarter of 2022. The time to complete this course varies, however graduate students enrolled in this course typically spend 10 weeks, 15-25 hrs/week. Hope this helps!
@@stanfordonlinegraduate students? Can I take it as an 2nd year CS undergrad? I'm fairly good with maths.
thx for uploading
Inshaalloh I'll get to Stanfrod
Nice Lecture!
와우~
멋진 강의네요👍👍👍👍👍👍
i really want to see the assingments from this course, does anyone know a way i can find them?
It's so great to be 12Kth in this course
i wish that you will share the computer vision course this year too
Is to possible to see ta lectures somewhere?
Thanks Stanford for sharing the knowledge across the world.
Could you also please help us where we can find the problem sets for the lecture series.
What are the objectives of this course? After doing this course are we able to build Machine Learning models?
Good🎉
The actual course starts at 18:10
any significant changes compared to the 2018 Andrew Ng course? i find this one easier to follow
I would like to know the same. Which one to follow.
have you gotten the answer for that?🙏
Well you should follow the most recent one as AI and machine learning evolves really quickly. This one is from 2022, a lot has happened in two years so you can already consider its partially outdated, still its very great content and a unique chance for everyone in the world to get access to that kind of high-level education.
kindly update about lectures notes how can i get notes??
Thanks Stanford for sharing this lecture. If you don't mind me asking, how soon can we expect the next lectures to come?
Hi there, thanks for your question and for watching! We will publish one new lecture per day for the next few weeks. The entire course will be available to view before the end of the month (August 2023).
@@stanfordonlineThank you so much for the helpful work that you are doing ! Merci beaucoup !
Could you please also upload videos of CS228 and CS236❤❤❤
Thanks for your comment, we will share your request with our team!
This massage show to me: 11 unavailable videos are hidden ... How can I watch all lecture in youtube?
jump to 18:11
Where can I find the problem set and the code of these lectures ?
What are prerequisites for these lectures?
7:06
Thanks for your question!
Prerequisites for CS229 - Students are expected to have the following background:
Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program in Python/NumPy. (CS106A or CS106B, CS106X.)
Familiarity with probability theory. (CS 109, MATH151, or STATS 116)
Familiarity with multivariable calculus and linear algebra (relevant classes include, but not limited to MATH 51, MATH 104, MATH 113, CS 205, CME 100.)
You can find more information on the course website: cs229.stanford.edu/syllabus-spring2022.html
If I don’t know multivariable calculus and linear algebra then learning ml is not possible ?
Multivariable calculus: treat other variables as constant when taking derivative/integral. Linear algebra: manipulate matrices and learn about vector spaces and bases. Not much to learn so yes is possible
They come not to teach but to take.
Focus on classes instead of looking comments LoL
Where can I access the PPT used by the professor
What is the syllabus used for this course?
Hi there, you can find the syllabus here: cs229.stanford.edu/syllabus-spring2022.html
@@stanfordonline thank you!
...It sounds like Tensun Ma (Tencent Ma, The Boss Ma of Tencent) to me...
18:10
1:00
Tengyu ma 也变成大叔了😁🤣
☺️☺️☺️☺️☺️❤️❤️❤️❤️
a
🥰💘🎯🙏✍🤝
开口一个投尼玛我真没绷住