TY - JOUR
T1 - Enhancing Hopfield network performance for pattern retrieval using sparse recovery algorithm and Parzen estimator
AU - Stanković, Djordje
AU - Draganić, Andjela
AU - Ioana, Cornel
AU - Orović, Irena
N1 - Publisher Copyright:
© 2024 Elsevier Inc.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - 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.
AB - 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.
KW - Gradient-descent algorithm
KW - Hopfield neural network
KW - Iterative signal recovery
KW - Parzen estimator
KW - Pattern retrieval
UR - http://www.scopus.com/inward/record.url?scp=85206475588&partnerID=8YFLogxK
U2 - 10.1016/j.dsp.2024.104814
DO - 10.1016/j.dsp.2024.104814
M3 - Article
AN - SCOPUS:85206475588
SN - 1051-2004
VL - 156
JO - Digital Signal Processing: A Review Journal
JF - Digital Signal Processing: A Review Journal
M1 - 104814
ER -