Generative AI Foundations on AWS | Part 6: RL with human feedback

In part 6 of Generative AI Foundations on AWS, AWS generative AI expert instructor Emily Webber will teach you about reinforcement learning with human feedback (RLHF) and why it is important.

You'll learn how it solves problems with subjectivity and objectivity through ranked human preference at scale before diving into how it works. Dive deep into original GPT, labelling from humans, reward models, and how to leverage reward model signal to update a new GPT model.

Subscribe:

Do you have technical AWS questions?

ABOUT AWS
Amazon Web Services (AWS) is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers — including the fastest-growing startups, largest enterprises, and leading government agencies — are using AWS to lower costs, become more agile, and innovate faster.

#AWSMachineLearning #MachineLearningUniversity #MLU #LearnML #LearnMachineLearning #aiml #GenerativeAI #GPT #AWS #AmazonWebServices #CloudComputing

[EricJonas-bi]

That was very easy to Learn Correctly all by myself! And I also understand all of these lessons at all the time! 😍

[araghuraman]

Great video. The interleaved statements about type, quantity and performance of hardware may be broken out into a separate video. May suffice to just mention how many GPUs/CPUs for the immediate scenario.

[ADV-IT]

Hm.. looks like less and less people got to this Part6 :)

[brightdarko]

I barely understand what is going on but i just stick to it to the end at least something will sink in and ill build from there