Score: 0

On Dimension-Free Transformer: An Application of STP to AI

Published: April 20, 2025 | arXiv ID: 2504.14514v1

By: Daizhan Cheng

Potential Business Impact:

Makes computer learning work with any size information.

Business Areas:
STEM Education Education, Science and Engineering

The matrix expressions for every parts of a transformer are firstly described. Based on semi-tensor product (STP) of matrices the hypervectors are reconsidered and the linear transformation over hypervectors is constructed by using projection. Its properties and calculating formulas are obtained. Using projection-based transformation of hypervector (PBTH), the framework of dimension-free transformer (DFT) is proposed by verifying each linear transformation in a transformer and replacing it by a proper PBTH, which allows the inputs and outputs being of arbitrary dimensions. Using balanced information about all entries, DFT must be more efficient in dealing with signals.

Page Count
17 pages

Category
Computer Science:
Machine Learning (CS)