Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Dive deep into the world of Transformer models in this comprehensive 44-minute video, the final installment of a three-part series. Explore the inner workings of these powerful machine learning models through visuals and friendly examples. Learn about key concepts such as tokenization, embeddings, positional encoding, attention mechanisms, and softmax. Understand how Transformers generate text one word at a time, perform sentiment analysis, and utilize neural networks. Discover the architecture of Transformer models and the process of fine-tuning. Perfect for those seeking to demystify this crucial technology in natural language processing and machine learning.
Syllabus
Introduction
What is a transformer?
Generating one word at a time
Sentiment Analysis
Neural Networks
Tokenization
Embeddings
Positional encoding
Attention
Softmax
Architecture of a Transformer
Fine-tuning
Conclusion
Taught by
Serrano.Academy