PolyU COMP5511
Artificial Intelligence Concepts
Sequence Modeling and The Transformer
Learning Objectives
- Compare Architectures: Differentiate between RNNs, LSTMs, and the Transformer architecture.
- Self-Attention Mechanism: Explain the 'Attention Is All You Need' paper and self-attention mechanisms.
- Encoders and Decoders: Understand the role of Encoders and Decoders in models like BERT and GPT.