Enhancing Hopfield network performance for pattern retrieval using sparse recovery algorithm and Parzen estimator

An improved pattern recovery approach that integrates the Hopfield neural network (HNN) with the iterative signal reconstruction and Parzen window-based classification is proposed. The HNN is observed as a form of associative memory network, used for various pattern recognition and optimization task...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Digital signal processing Jg. 156; S. 104814
Hauptverfasser: Stanković, Djordje, Draganić, Andjela, Ioana, Cornel, Orović, Irena
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.01.2025
Elsevier
Schlagworte:
Engineering Sciences
Gradient-descent algorithm
Hopfield neural network
Iterative signal recovery
Parzen estimator
Pattern retrieval
Parzen estimator
Iterative signal recovery
Hopfield neural network
Gradient-descent algorithm
Pattern retrieval
ISSN:1051-2004, 1095-4333
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:An improved pattern recovery approach that integrates the Hopfield neural network (HNN) with the iterative signal reconstruction and Parzen window-based classification is proposed. The HNN is observed as a form of associative memory network, used for various pattern recognition and optimization tasks. However, when the input pattern is highly damaged with a very limited set of available samples, the Hopfield network fails to perform the retrieval. The convex optimization-based gradient descent algorithm is considered for pattern recovery of damaged inputs in order to provide an improved pattern approximation for further processing within the HNN, enabling successful network performance. Additionally, in the case of grayscale images, the Parzen window approach is used to classify the probability density functions (pdfs) of the training set and to choose those being comparable to the pdf of the input pattern, therefore refining the selection of patterns and providing better convergence to the exact retrieval. The theoretical considerations are verified experimentally, showing the high performance of the proposed approach when only 10 % of the pixels are available for binary patterns and 40 % of pixels for grayscale patterns.
ISSN:1051-2004
1095-4333
DOI:10.1016/j.dsp.2024.104814