In the realm of theoretical physics and machine learning, the intertwined world of network dynamics and computational intelligence opens up new horizons for research. This dissertation aims to contribute to this flourishing field by tackling two diverse yet deeply connected aspects: Neural Network Interpretability and Signal Dynamics in Simplicial Complexes. Both avenues explore the fundamental role played by spectral properties in shaping the behavior and capabilities of network systems.
A Journey Through Reciprocal Space: from Deep Spectral Learning to Topological Signals / Giambagli Lorenzo. - (2024).
A Journey Through Reciprocal Space: from Deep Spectral Learning to Topological Signals
Giambagli Lorenzo
Writing – Original Draft Preparation
2024
Abstract
In the realm of theoretical physics and machine learning, the intertwined world of network dynamics and computational intelligence opens up new horizons for research. This dissertation aims to contribute to this flourishing field by tackling two diverse yet deeply connected aspects: Neural Network Interpretability and Signal Dynamics in Simplicial Complexes. Both avenues explore the fundamental role played by spectral properties in shaping the behavior and capabilities of network systems.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Tesi Dottorato.pdf
accesso aperto
Descrizione: Tesi di Dottorato Lorenzo Giambagli
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
Open Access
Dimensione
14.45 MB
Formato
Adobe PDF
|
14.45 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
