FPGA Simulation for Computing Pseudoinverse Matrices

Many scientific and engineering processing models of big data deal with classification tasks. In particular, current intelligent approaches work efficiently for them, as they use neural techniques with shallow architectures. The Extreme Learning Machine (ELM), which is a one-hidden layer feedforward...

Full description

Saved in:
Bibliographic Details
Published in2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) pp. 1 - 4
Main Authors Tornez Xavier, Gerardo Marcos, Martin Flores Nava, Luis, Castaneda, Felipe Gomez, Antonio Moreno Cadenas, Jose
Format Conference Proceeding
LanguageEnglish
Published IEEE 25.10.2023
Subjects
Computational modeling
Electrical engineering computing
Extreme Learning Machine
Extreme learning machines
FPGA Simulation
Numerical models
Numerical simulation
Pseudoinverse
Real-time systems
Recurrent neural networks
Online AccessGet full text

Cover

More Information
Summary:Many scientific and engineering processing models of big data deal with classification tasks. In particular, current intelligent approaches work efficiently for them, as they use neural techniques with shallow architectures. The Extreme Learning Machine (ELM), which is a one-hidden layer feedforward neural network, is capable of achieving high accuracy in these tasks. Moreover, one of its weighting matrices is the pseudoinverse of the hidden data. In this sense, this work presents meaningful results of computing the Moore-Penrose pseudoinverse for the ELM, using a recurrent model. The numerical simulations were based on an FPGA framework used to design a pseudoinverse-computing core.
ISSN:2642-3766
DOI:10.1109/CCE60043.2023.10332880