DTA

Digital Theses Archive

 

Tesi etd-10262022-215344

Type of thesis
Corso Ordinario Secondo Livello
Author
MANCINI, RICCARDO
URN
etd-10262022-215344
Title
High Performance implementation of Self Organizing Maps on multiprocessor and GPU architectures
Structure
Cl. Sc. Sperimentali - Ingegneria
Course
INGEGNERIA - INGEGNERIA
Committee
relatore Prof. CUCINOTTA, TOMMASO
Presidente Prof. AVIZZANO, CARLO ALBERTO
Membro Dott. LEONARDIS, DANIELE
Membro Prof. CIPRIANI, CHRISTIAN
Membro Prof. DI PASQUALE, FABRIZIO CESARE FILIPPO
Membro Prof. FORESTIERI, ENRICO
Membro Prof.ssa MENCIASSI, ARIANNA
Membro Prof. MICERA, SILVESTRO
Membro Prof. VITIELLO, NICOLA
Membro Prof. ABENI, LUCA
Membro Prof. BIONDI, ALESSANDRO
Membro Dott.ssa COLLA, VALENTINA
Keywords
  • cupy
  • gp-gpu
  • kohonen maps
  • numpy
  • python
  • self-organizing maps
Exam session start date
14/12/2022;
Availability
completa
Abstract
Self Organizing Maps (SOMs) are a kind of unsupervised, shallow, artificial neural networks, built on top of the competitive learning principle and typically employed for clustering, dimensionality reduction and high-dimensional data visualization.<br>In this work, a novel, high-performance, and parallel implementation of SOM is designed, implemented, and evaluated on openly available datasets.<br>
Files