Weeks 14 and 15: Training and Using Large Language Models Attention and Transformer Networks

Learning Objectives

Concepts

Without any programming, you should be able to:

• Relate each component of the English to Portuguese translator to attention and transformer networks, especially which parts are used for the attention encoding, the attention decoding, and the transformer.

Implementation

Using the Python programming language, you should be able to:

• Use the Keras and Tensorflow libraries and the given code to implement an English to Portuguese translator including explaining the purpose of the given code and altering the given code to improve its function or add additional functionality.
• Relate each component of the English to Portuguese translator to attention and transformer networks