Part 4: Transformers beyond NLP
Chapter 16 elaborates on the concept of vision transformers, a revolutionary approach that applies transformer-based models to computer vision tasks, providing a different perspective from traditional convolutional neural networks.
In Chapter 17, the focus shifts to Multimodal Generative Transformers, a sophisticated model that can generate complex output spanning multiple modalities, demonstrating the versatility and power of transformer models.
Lastly, Chapter 18 delves into time series modeling with Transformers, exploring how these models can be adeptly used to analyze and predict sequential data, thereby broadening their application beyond natural language processing.
This part has the following chapters:
- Chapter 16, Vision Transformers
- Chapter 17, Multimodal Generative Transformers
- Chapter 18, Revisiting Transformers Architecture for Time Series
