10 websites where you can learn anything for free:

1. Udemy

Udemy is an online learning and teaching marketplace with over 185000 courses and 49 million students.

Although most of the courses were premium on this site, some of them were available for free.

https://t.co/jU3ZSQ05Vk
2. Edx

EdX is a learning platform that gives students from any country the opportunity to take free online courses offered by premier Universities such as Harvard and MIT

https://t.co/53C9apcLYW
3. Instructables

Instructables is a website specializing in user-created and uploaded do-it-yourself projects, which other users can comment on and rate for quality.

https://t.co/5EphUXDX3D
4. Cooksmarts

Cook Smart is the exciting way to learn new recipes & improve cooking skills while using any device. Learn from top-notch professional chefs.

https://t.co/imc0hioTVE
5. TedEd

TED-Ed platform allows users to take any TED Talk, TED-Ed Lesson or educational video and easily create a lesson plan of customized questions and discussions.

https://t.co/jxxrGixHbD
6. Khan Academy

Learn for free about math, art, computer programming, economics, physics, chemistry, biology, medicine, finance, history, and more.

https://t.co/NhtUpGbd2b
7. Skillshare

Skillshare is an online learning platform with thousands of creative courses and classes taught by experts to help you learn new skills.

https://t.co/dwcmFhJibH
8. OpenLearn

OpenLearn create hosts collections of courses created by teachers, colleges, universities, organisations and individuals from around the world.
https://t.co/mMqFWD9380
9. FutureLearn

Join millions of people learning on FutureLearn. Find online courses and degrees from leading universities or organizations and start learning online today.

https://t.co/MpgUEiaQ3y
10. Degreed

Degreed is the upskilling platform that connects learning, talent development, and internal mobility opportunities in one place.

https://t.co/wJnOsKFsal

More from All

How can we use language supervision to learn better visual representations for robotics?

Introducing Voltron: Language-Driven Representation Learning for Robotics!

Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z

🧵👇(1 / 12)


Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.

Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)

The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (
https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).

The secret is *balance* (3/12)

Starting with a masked autoencoder over frames from these video clips, make a choice:

1) Condition on language and improve our ability to reconstruct the scene.

2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)

By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.

Why is the ability to shape this balance important? (5/12)

You May Also Like