Applying category theory to improve the performance of a neural architecture |
| |
Authors: | Michael J. Richard D. Robert J. Shawn E. Thomas Kurt W. |
| |
Affiliation: | aDepartment of Electrical and Computer Engineering, University of New Mexico, USA;bDepartment of Computer Science, University of New Mexico, USA;cSandia National Laboratories, Albuquerque, New Mexico, USA |
| |
Abstract: | A recently developed mathematical semantic theory explains the relationship between knowledge and its representation in connectionist systems. The semantic theory is based upon category theory, the mathematical theory of structure. A product of its explanatory capability is a set of principles to guide the design of future neural architectures and enhancements to existing designs. We claim that this mathematical semantic approach to network design is an effective basis for advancing the state of the art. We offer two experiments to support this claim. One of these involves multispectral imaging using data from a satellite camera. |
| |
Keywords: | Category theory Mathematical semantics ART 1 Stack intervals Multispectral imaging |
本文献已被 ScienceDirect 等数据库收录! |