This is the second teaser the seminar series I’m giving on LLMs. This is taken from the third in the series which examines how the attention mechanism works. You can sign up here.

The agenda is as follows:

• Session 1: Neural Networks, their structure, matrix representation, feed forward processing and back propagation.
• Session 2: Embeddings, how they are computed and different ways you can use them.
• Session 3: Attention, how it works, the matrix math behind it and how it solves the context problem with embeddings.
• Session 4: An overview of the Transformer, how it works, how it’s trained and how it produces such uncanny results.