Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions

arXiv:2305.12205v2 Announce Type: replace
Abstract: In recent years, deep learning-based sequence modelings, such as language models, have received much attention and success, which pushes researchers to explore the possibility of transforming non-sequential problems into a sequential form. Following this thought, deep neural networks can be represented as composite functions of a sequence of mappings, linear or nonlinear, where each composition can be viewed as a \emph{word}. However, the weights of linear mappings are undetermined and hence require an infinite number …

abstract approximation arxiv attention cs.lg cs.na deep learning explore form functions language language models mapping math.ds math.na networks neural networks perspective possibility replace researchers success thought type universal