Mydra logo
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Embedding Models: From Architecture to Implementation

  • up to 1 hour
  • Beginner

Join this short course to gain an in-depth understanding of embedding models, from architecture to implementation. Learn from Ofer Mendelevitch and explore the evolution of embedding models, including Word2Vec and BERT, and their applications in semantic search systems.

  • Embedding models
  • Semantic search
  • Transformer models
  • Dual encoder architecture
  • Contrastive loss

Overview

This course offers a comprehensive exploration of embedding models, focusing on their architecture and implementation. Participants will learn about word and sentence embeddings, dual encoder models, and the use of contrastive loss to enhance question-answer retrieval applications. The course provides a hands-on approach to understanding the technical concepts behind embedding models, making it ideal for data scientists, machine learning engineers, and NLP enthusiasts.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Data Scientists

Professionals looking to enhance their understanding of embedding models and their applications in AI.

Machine Learning Engineers

Engineers interested in learning about the architecture and implementation of embedding models.

NLP Enthusiasts

Individuals passionate about natural language processing and semantic retrieval systems.

This course provides a deep dive into embedding models, crucial for building semantic retrieval systems. Ideal for beginners and professionals, it covers key concepts like Word2Vec, BERT, and dual encoder models, helping learners advance their careers in AI and machine learning.

Pre-Requisites

1 / 3

  • Basic Python knowledge

  • Familiarity with AI applications

  • Understanding of semantic search systems

What will you learn?

Introduction
An overview of the course and its objectives.
Introduction to embedding models
Understanding the basics of embedding models and their applications.
Contextualized token embeddings
Exploring token embeddings with code examples.
Token vs. sentence embedding
Comparing token and sentence embeddings with practical examples.
Training a dual encoder
Learning how to train dual encoder models using contrastive loss.
Using embeddings in RAG
Implementing embeddings in a RAG pipeline with code examples.
Conclusion
Summarizing the key learnings from the course.
Quiz
A short quiz to test your understanding of the course material.
Appendix – Tips and Help
Additional resources and tips for further learning.

Upcoming cohorts

  • Dates

    start now

Free