Jeff Dean’s Lecture for YC AI

7 thoughts on “Jeff Dean’s Lecture for YC AI”

1. good

2. Learning to learn for sure

3. @45:42 "and robotics I think is at an inflection point, where, through machine learning for control we're going to have robots that can actually operate in messy environments like this one or in the kitchen over there, and actually know how to manipulate things in a safe way with humans"
   Do you think Jeff Dean said that with only a focus to applying machine learning to advancements in planning and policy, and not perception?

4. awesome presentation and even better questions at the end

5. He may be like the most intelligent person you’ve never heard of, and I salute the incredible things he has done at google…but he can’t present for shi…..

6. I would be curious to see if, going along with this 'learning to learn' task, that we could use gans to generate similar, but different problems. RL could be used to keep the difference between two problems in check and start to recognize when it can challenge itself in taking on new tasks more.
   For example, I'm thinking about like going from image classification of like 100 x 100, then a GAN tells the RL NAS to go to 101 x 101. Next it generates a problem with two frames (a video), then it starts learning speech and sound source detection. Building on itself to increase data efficiency.

7. Thank you Jeff Dean.

Comments are closed.