Awesome...very entertaining as well as informative. Thanks Paul for creating this entertaining presentation to explain a complex subject like machine learning. Looking forward for more presentation like this. God bless you!!
That was lovely! The next time Siri gives a talk, she needs to ask you to feed the dogs... so that you've got something useful to do. In all seriousness, I took a 12 week course on Data Science at a California university, and you (ahem, I mean Siri) pretty much summed up at least three sessions in one 45 min. talk.
Really great, but it seems CreateMLUI no longer exists in XCode 13. There is a CreateML module, but it's not the same. Maybe Siri can redo this, if she has the time? ;)
Every time I see a demo of image classification training in CoreML I’m left to wonder why an app developer would do this. Aren’t there already pre-trained models for the most common image classifiers? I’m struggling to think of examples where an app developer needs to train their own. I guess insect and plant classifiers might not exist already. But then the problem I see is one of creating a large enough corpus of training data. Can you give us any real-world examples of developer-provided training, and talk about what they had to do to get the training data?
Well, if you were building an app to recognize sign language, that would take a lot of recognition work, particularly if you weren't training for one of the major sign languages, such as ASL. There is a large and ongoing debate in the ML world about whether it's harder to improve algorithms or get more training data, and in my view the latter is harder by far - anyone can write code and throw 10,000 GPUs at it, but getting 100 different photos of the same hand gesture, with varying skin tones, lighting, angles, and more, is hard. Fortunately for all of us, sites like Kaggle share lots of existing training data, which is a good start.
It would be nice if you could get a terminal session on the iPhone and tell it to up it’s Siri game. TBH, Siri had no problem recognizing my question about ML, though!
OMG! Great video! Lots of support from Russia. We have a question if you don't mind, do you know how we could use ar to automatically measure somebody's height? We would want to point the camera at a person and it to measure their height automatically, do you know how to do that by any chance? Don't worry if you don't get around to answering this, you are probably very busy. Thanks so much anyways and continue with the great content!
What's the updated code to get the playground running in Xcode 15? Anyone? I mean.... I guess I could give chatGPT a try & see if it can convert the code...
This is the most crafty tutorial I've ever seen!🔥🔥
I absolutly love this video concept of Siri explaining CoreML! Amazing job, Paul. Thank you for this video!
This is totally out of the box presentation. A total artwork.
I was tired and ready to end my day, then I started watching and couldn’t stop. Fantastic job!
I don't know anything about coding yet this taught me so much. Thank you for opening my eyes to the incredible ML resources apple offers!
The best ML Tutorial ever, I'm completely hooked 🔥🔥🔥🔥🔥🔥
This was the greatest video on ML I have ever seen. Wish YT would have recommended it sooner 🤣
What a brilliant talk! It's highly informative, extremely well-designed, and hilarious. Bravo, Paul! 👏 Thank you a ton for this incredible job!
Awesome...very entertaining as well as informative. Thanks Paul for creating this entertaining presentation to explain a complex subject like machine learning.
Looking forward for more presentation like this.
God bless you!!
the sentiment analysis for this video's comment section would give you a really positive result paul!
This is another amazing body of hard work from Paul Hudson. Thank you!
Good job Paul, that was absolutely genius & funny way to learn ML
thx :)
Hey, Paul 👋🏼 I`ve found your channel just a week ago and I am totally impressed. Thank you for your work 😌 That's amazing!
I thought ML was going to be scary and complicated… after watching this entertaining video I feel confident to play with it! Thank you ❤
That was lovely! The next time Siri gives a talk, she needs to ask you to feed the dogs... so that you've got something useful to do. In all seriousness, I took a 12 week course on Data Science at a California university, and you (ahem, I mean Siri) pretty much summed up at least three sessions in one 45 min. talk.
I must say it was an amazing work. One of the best videos for software developers.
Absolutely genius. Great video Paul.
This is a brilliant video like WOAH. Keep on being creative love the work :>
You are a genius. I'm so happy I'm learning from you!
That was really entertaining and I learned a lot. Thanks Paul.
Level 6 is when Siri becomes self aware
This is the perfect video possible to get introduced to ML on Mac/iOS _
Paul’s Creativity level _ infinity 😄
This deserves way more views!
Amazing episode Paul, loved the creativity!
Great video, I love it, very funny, very informative. Gotta say Paul, you have outdone yourself!
Really great, but it seems CreateMLUI no longer exists in XCode 13. There is a CreateML module, but it's not the same. Maybe Siri can redo this, if she has the time? ;)
let str = "Paul is a Master Trainer in SWIFT. Paul creates engaging videos. "
let replaced = str.replacingOccurrences(of: "Paul", with: "Siri")
:)
Excellent and funny way to present this subject Paul
🙌🏻🙌🏻🙌🏻🙌🏻
entertaining and informative.. can't be any better, thanks a lot
I learned so much in this video, the work was phenomenal thank you 🙏
Nice work, just starting out with coreML and CreateML
I love this ❤️ imagine add it to your app for customers services
Hilarious Paul!! Very creative teaching approach!
Man I never see this coming "Siri taking over from paul "
@twostraws you are genius and a great teacher.
15:03 Data augmentation (with not so many training data)
Siri is an excellent Teaching Assistant for you, or is that the other way around? Great video, thank you!
Great tutorial and incredible fun to watch LOL
Thanks Paul. Great idea and video 😃👏
Hi, Paul! Entertaining and informative. Great work!
had a good chuckle whilst learning a lot. cheers.
Hello, Does the siri-ai still works? I tried to do it on my mac today but its not working...
You are so funny and so smarty !! One of the best tutorial ever. Mean it!
Excellent work Paul, keep it up!
Can you share the link to Slides?
Great video! A machine helping to learn Machine Learning, I like that
Paul you should have released this on the 1st of April! :D
Why can't I import CreateMLUI on Xcode 12 and MacOS Big Sur, of course I 've already selected MacOS playground
Lol smarter Siri! That’s a great little nugget of info
Paul, you are the best!
Every time I see a demo of image classification training in CoreML I’m left to wonder why an app developer would do this. Aren’t there already pre-trained models for the most common image classifiers? I’m struggling to think of examples where an app developer needs to train their own.
I guess insect and plant classifiers might not exist already. But then the problem I see is one of creating a large enough corpus of training data.
Can you give us any real-world examples of developer-provided training, and talk about what they had to do to get the training data?
Well, if you were building an app to recognize sign language, that would take a lot of recognition work, particularly if you weren't training for one of the major sign languages, such as ASL. There is a large and ongoing debate in the ML world about whether it's harder to improve algorithms or get more training data, and in my view the latter is harder by far - anyone can write code and throw 10,000 GPUs at it, but getting 100 different photos of the same hand gesture, with varying skin tones, lighting, angles, and more, is hard. Fortunately for all of us, sites like Kaggle share lots of existing training data, which is a good start.
OMG how did you do the Siri dialogues 😅??
It would be nice if you could get a terminal session on the iPhone and tell it to up it’s Siri game. TBH, Siri had no problem recognizing my question about ML, though!
OMG! Great video! Lots of support from Russia.
We have a question if you don't mind, do you know how we could use ar to automatically measure somebody's height? We would want to point the camera at a person and it to measure their height automatically, do you know how to do that by any chance?
Don't worry if you don't get around to answering this, you are probably very busy. Thanks so much anyways and continue with the great content!
Fast forward 2022 Siri can now answer "What is machine learning? " without the command line script executed
oh my gosh... the funniest tutorial ever! 🤣 thanks, Paul... äh, Siri 😉
What's the updated code to get the playground running in Xcode 15? Anyone? I mean.... I guess I could give chatGPT a try & see if it can convert the code...
I love it , Thanks Paul
Loved this tutorial
I love your videos so much...!
Got to know ML much better now. tx!
Mind blowing! Thanks a lot !
This is brilliant
That was next level 😁
hahaah great video!!! thank you :) Was fun
Just outstanding !
lol how did I mess up so fast... my Playground is telling me there is no 'CreateMLUI' module. 🤔
Ah, I see it in the video now, (and was pointed this way by the dev forums) but it needs to be a macOS playground, not iOS 😁
Now imagine what happens if you put all those straws into a large vanilla malt... now I’m getting hungry. 🤗
What a Show !
Had me for a second there.
Please update this video. I think it is outdated.
Love it!
Haha, very well done.
You are a god among men
really good
Incredible
Fantastic creativity and well explained. 🤣
Siri is the most powerful machine learning system :) It's so funny to hear this in 2023. Siri is useless. All she can do is call someone.
sorry. It was a sarcasm. I wrote my comment too early. 5 of 5
why two straws?
best of the best !
THANK YOU SIRI!!!! 🤣
Bahahhaha seriously that's fuN! Thanks!
Lol.. very interesting!
Genius
Bravo
✨👍🏻
I like siri
Wow
🤣🤣🤣🤣🤣
LOL