What you'll learn

Traditional neural networks, like recurrent neural networks (RNNs), struggle with long-range dependencies and slow, sequential processing—limitations that transformers were designed to overcome.

In this course, Transformers and LLMs, you’ll understand how transformers have revolutionized modern AI.

First, you’ll explore the challenges of recurrent models and why attention mechanisms were needed.

Next, you’ll discover how the transformer’s encoder-decoder structure and multi-head attention enable faster, more contextual learning.

Finally, you’ll learn how self-attention computes relationships across entire sequences in parallel.

When you’re finished with this course, you’ll have the knowledge of transformer and LLM fundamentals needed to interpret, apply, and discuss how these models power today’s most advanced AI systems.