These TensorFlow updates are huuuuuuuuge! [Google I/O 2021] | Machine Learning Monthly May 2021

Machine learning monthly covers the latest and greatest (but not always the latest) of the machine learning field from the previous month. You can expect exciting machine learning updates as well as dancing.
ML Monthly May 2021 - zerotomastery.io/blog/machine...
Learn ML (beginner-friendly course) - dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - dbourke.link/tfcourse
Connect elsewhere:
Web - dbourke.link/web
Twitch - / mrdbourke
ArXiv channel (past streams) - / @danielbourkearxiv2821
Get email updates on my work - dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:24 - Google IO 2021
1:03 - Google's On-device Machine Learning Page
1:43 - TensorFlow Lite Models are now compatible with TensorFlow.js
2:28 - Create your own TensorFlow Lite models with the new Model Maker library
3:13 - TensorFlow Hub Upgrades
4:00 - TensorFlow Cloud (run your small experiments at cloud scale)
4:48 - Vertex AI (Google Cloud's new one-stop-shop for everything machine learning)
5:31 - The Practitioner's Guide to MLOps White Paper
6:13 - The new TensorFlow Town Square (TensorFlow Forum)
6:37 - People and AI Guidebook 2.0
7:53 - Know Your Data tool (beta)
8:32 - Where to learn more about Google IO ML & TensorFlow updates
8:57 - Next generation pose detection with MoveNet and TensorFlow.js
9:57 - Datasets and code on arXiv (thanks to paperswithcode)
10:31 - wav2vec-U (high performance speech recognition with no supervision)
12:14 - What is active learning? blog post by Roboflow
13:17 - Reproducible Deep Learning course by Simone Scardapane
14:25 - The Rise of HuggingFace by Mark Saroufim
15:06 - Outro & 🕺
#machinelearning #mlmontly

[@ChaiTimeDataScience]

Came here for ML, Stayed for the dance! At this point, I don't think there's anything that the multi-talented Daniel can't do :D

[@mrdbourke]

If you’re after ML + dance, you’ve come to the right place

[@murjoshua]

"You know when you stumble upon a little piece of someone's work, and then quickly consume everything they've ever created? That's what happened when I found:" Daniel Bourke! Great contents, thanks allot for putting it all out!

[@nathancooper1001]

Production quality is getting really good!! Really enjoyed this installment

[@mrdbourke]

Thank you Nathan! A little different to last episode(s)

[@lonwulf0]

I didn't have time to follow Google I/O closely but your videos are really great to keep me updated, Great work keep it up.

[@mrdbourke]

You’re welcome, stoked you enjoyed!

[@RedMaster-mw6ti]

This guy. This guy giving updates unlike our teenage daughters not answering your text messages.

[@mrdbourke]

😂

[@yashnaik9914]

Thanks a ton Daniel! Your videos based on your Machine Learning Monthly articles are super helpful. Keep up the good work!

[@mrdbourke]

Thank you Yash!

[@amadeusml]

Awesome content, thanks!

[@yashpatel-wk7td]

I was wondering you would include these updates in Machine Learning Monthly, which is why I was waiting for this video before going through Myself because the way you make these videos spark the curiosity 💯 ..!!

[@grumly85]

Keep dancing!

[@tinylittleanj2]

That’s brilliant!!

[@erentas7391]

You are doing your best again.

[@mrdbourke]

[@egehurturk6209]

Your videos are lit!

[@saradhapaudel9344]

Can you review the AppliedAI course?? Lots of Love!

[@spicytuna08]

thanks daniel!!!

[@paulntalo1425]

An awesome piece for AI enthusiasts. thank you

[@theunusualhacker6118]

Sir I am taking your tensorflow course. Is it possible that you make a course on tensorflow lite or tensorflow js. I feel that's awesome after learning tensorflow.

[@gauravreddy3732]

Been Waiting for this since the last one !!!

[@mrdbourke]

Your patience has been rewarded

[@minma02262]

I like this month's coverage! Can you talk about why reproducible ML is important and when it is relevant? Came for the content, stayed for the person! Thank you!

[@sunilswaroop7036]

Do you have any courses on Theoretical ML?

[@jithendrayenugula7137]

your dance is soo coool ;) also, thanks for making this content daniel

[@mrdbourke]

Thank you! Glad you enjoyed 🕺

[@Fjifjdjfkfjdhfijvu2]

will you update your tenserflow course ?

[@mrdbourke]

If you’ve done the TensorFlow course, you’ll have the skills to learn these updates yourself

[@airepublic9864]

12:30 so basiclly we dont need to label everything, we cluster them then label the clusters woooooow

[@mrdbourke]

Yep, in machine learning there’s often more than one way of doing things

[@liy1561]

never been this early, ever

[@mrdbourke]

A new record!

[@manansingla9543]

👍👍

[@markcuello5]

Help me

[@henryhe4387]

hi, Daniel: super star teacher. how to follow you to learn and product ML&CV, a few days ago , i sent you email, thanks

[@variable5091]

Could you personally teach me ML and take me from o to 70 level as there is no end of learning I won't say 100.... But 70

[@sudhar6516]

He has a machine learning course on Udemy

[@mrdbourke]

Mayukha is right! I teach two courses, almost 100-hours worth of ML + checkout the ML roadmap video on my channel, that’ll help too

[@taransanger3273]

First now pin me plsss

[@mrdbourke]

Hahaha so close, Liy got first though