- Level Professional
- المدة 2 ساعات hours
-
Offered by
عن
In this 2 hour long project, you will learn how to preprocess a text dataset comprising recipes, and split it into a training and validation set. You will learn how to use the HuggingFace library to fine-tune a deep, generative model, and specifically how to train such a model on Google Colab. Finally, you will learn how to use GPT-2 effectively to create realistic and unique recipes from lists of ingredients based on the aforementioned dataset. This project aims to teach you how to fine-tune a large-scale model, and the sheer magnitude of resources it takes for these models to learn. You will also learn about knowledge distillation and its efficacy in use cases such as this one. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.Auto Summary
Embark on an exciting journey into the world of data science and artificial intelligence with the "Generating New Recipes using GPT-2" course on Coursera. This immersive, two-hour project is designed for intermediate learners eager to expand their skills in text data preprocessing and model training. Under the expert guidance of seasoned instructors, you’ll delve into the intricacies of preparing a text dataset filled with recipes, learning to split this data into effective training and validation sets. The course offers a hands-on approach, ensuring you gain practical experience with GPT-2, one of the most advanced AI models for generating human-like text. Perfect for those with a foundational understanding of data science, this project is available for free, making it an accessible opportunity to enhance your AI capabilities. Whether you're a data enthusiast or a professional looking to sharpen your skills, this course provides the tools and knowledge to innovate in the culinary domain through cutting-edge technology.