conftrace_

transformer expressive power

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

approximation property (1) feed-forward layer (1) long-range dependency (1) positional encoding (1) approximation theory (1) expressive power (1) theoretical analysis (1) attention mechanism (1) sequence modeling (1)

Papers

Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NeurIPS 2024