Global Admissions Logo

$ USD

Search Programs

Reinforcement Learning from Human Feedback

California, United States

The Non-degree in Reinforcement Learning from Human Feedback at DeepLearning.AI is a program for international students taught in English.

đź“– Introduction

DeepLearning.AI is an online education platform founded in 2017 by Andrew Ng, a leading AI expert and co-founder of Coursera. As a private organization, DeepLearning.AI specializes in AI and machine learning education, offering high-quality courses, specializations, and professional certifications in collaboration with top institutions and industry leaders. The platform is known for its practical, hands-on approach to teaching AI concepts and its focus on making cutting-edge AI knowledge accessible to learners worldwide.

📚 About the Program

Large language models (LLMs) are trained on human-generated text, but additional methods are needed to align an LLM with human values and preferences.Reinforcement Learning from Human Feedback (RLHF) is currently the main method for aligning LLMs with human values and preferences. RLHF is also used for further tuning a base LLM to align with values and preferences that are specific to your use case. In this course, you will gain a conceptual understanding of the RLHF training process, and then practice applying RLHF to tune an LLM. You will: 1. Explore the two datasets that are used in RLHF training: the “preference” and “prompt” datasets.2. Use the open source Google Cloud Pipeline Components Library, to fine-tune the Llama 2 model with RLHF.3. Assess the tuned LLM against the original base model by comparing loss curves and using the “Side-by-Side (SxS)” method.

Large language models (LLMs) are trained on human-generated text, but additional methods are needed to align an LLM with human values and preferences.Reinforcement Learning from Human Feedback (RLHF) is currently the main method for aligning LLMs with human values and preferences. RLHF is also used for further tuning a base LLM to align with values and preferences that are specific to your use case. In this course, you will gain a conceptual understanding of the RLHF training process, and then practice applying RLHF to tune an LLM. You will: 1. Explore the two datasets that are used in RLHF training: the “preference” and “prompt” datasets.2. Use the open source Google Cloud Pipeline Components Library, to fine-tune the Llama 2 model with RLHF.3. Assess the tuned LLM against the original base model by comparing loss curves and using the “Side-by-Side (SxS)” method.

🏫 About the University

DeepLearning.AI is dedicated to advancing artificial intelligence education and empowering individuals to build careers in AI and machine learning. The platform offers a range of courses, including the renowned "Deep Learning Specialization" and "AI for Everyone," designed to cater to beginners, professionals, and researchers. By collaborating with leading experts and institutions, DeepLearning.AI provides industry-relevant content that bridges the gap between theoretical knowledge and real-world applications. Through its online courses, research initiatives, and community-driven projects, DeepLearning.AI plays a crucial role in shaping the future of AI education and innovation.

đź’° Fees

Application Fee

$0 USD

$0 USD

Tuition Fee

$120 USD

$120 USD

per year

âś… Entry Requirements

The minimum age is 18 and the maximum age is 50.

English Fluent is required.

Minimum education level Bachelor's degree

All students from all countries are eligible to apply to this program.

📬 Admissions Process


1

Step 1

Choose programs

2

Step 2

Apply online

3

Step 3

Enroll

📝 Reviews

Write a review

Application Fee

$0 USD

Service Fee

$0 USD

Tuition

$120 USD

Why Apply on Global Admissions?

Similar Programs to Non-degree

Similar Programs to Non-degree

We use cookies to improve your experience and analyze site usage. Read our Privacy Policy to learn more about our data practices.