Hyperbolic Hopfield neural networks for image classification in content-based image retrieval

Abstract

Neural networks play a significant role in data classification. Complex-valued Hopfield Neural Network (CHNN) is mostly used in various fields including the image classification. Though CHNN has proven its credibility in the classification task, it has a few issues. Activation function of complex-valued neuron maps to a unit circle in the complex plane affecting the resolution factor, flexibility and compatibility to changes, during adaptation in retrieval systems. The proposed work demonstrates Content-Based Image Retrieval System (CBIR) with Hyperbolic Hopfield Neural Networks (HHNN), an analogue of CHNN for classifying images. Activation function of the Hyperbolic neuron is not cyclic in hyperbolic plane. The images are mathematically represented and indexed using the six basic features. The proposed HHNN classifier is trained, tested and evaluated through extensive experiments considering individual features and four combined features for indexing. The obtained results prove that HHNN guides retrieval process, enhances system performance and minimizes the cost of implementing Neural Network Classifier-based image retrieval system.

Assessing High and Low-Risk Bank Loan Approvals

“…The Random Forest objective is to figure out advance acknowledgment forecast techniques and, at last, valuing systems for Jordanian microfinance items by concentrating on the client behaviour [21]. Our group has broad information and exploration experience that has convert into great distributions [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36]. Accordingly, the review results produce better execution in both test and factual investigation, yet it has a few constraints to the proposed work.…”

A direct analysis method to state bounding for high‐order quaternion Hopfield neural networks with mixed delays and bounded disturbances

“…kind of neural network similar to human brain, which is used to store and extract memories. It has been widely concerned for dealing with some problems such as cell model identification, 2 image retrieval, 3 and recognition indication. 4 The prevalence of quaternion neural network (QNN) theory is uninterruptedly enhanced of late years.…”