An Introduction to Transformers
This is an incremental contribution aimed at researchers and practitioners in machine learning seeking a clearer understanding of transformers.
The authors tackled the problem of existing introductions to transformers lacking precise mathematical descriptions and clear intuitions for design choices, resulting in a note that provides a mathematically precise, intuitive, and clean description of the transformer architecture.
The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and spatio-temporal modelling. There are many introductions to transformers, but most do not contain precise mathematical descriptions of the architecture and the intuitions behind the design choices are often also missing. Moreover, as research takes a winding path, the explanations for the components of the transformer can be idiosyncratic. In this note we aim for a mathematically precise, intuitive, and clean description of the transformer architecture. We will not discuss training as this is rather standard. We assume that the reader is familiar with fundamental topics in machine learning including multi-layer perceptrons, linear transformations, softmax functions and basic probability.