International Conference on Open Source Systems and Technologies (ICOSST)

Dynamic ontologies evaluation framework using quantum perceptron neural network

Shahid Naseem

Published Dec 1, 2015• 1 citation

Abstract

Ontologies can be built on systems that can evolve continuously. Ontologies analysis and appraisal are performed for measuring the eminence of an ontology. Ontologies evaluation is used to automatically reveal conceivability problems. For evaluating dynamic ontologies in semantic web and to set the weights to the neurons, Classical Neural Network (CNN) has to face a number of challenges such as the absence of discrete algorithm, limited memory capacity, time-consuming training due to the declarative nature of ontologies. CNN cannot provide low-cost learning. In CNN, data is non-linear and hard to analyze. Recently, with the rapid development of technology, there are a lot of applications such as dynamic ontologies creation and evaluation require to low-slung learning cost. However, the computational power of CNN, is that it cannot provide low-slung learning cost. On the other hand, Quantum Neural Network (QNN) can be a good computational network instead of CNN approaches. In this paper, we present a new computational approach for dynamic ontologies evaluation to the Quantum Perceptron Neural Network (QPNN) can achieve low-slung learning cost. The proposed Quantum Neural Network can construct self-adaptive activation operators that have the capability to accomplish the learning process in a limited number of iterations and thereby, reduce the overall computational cost. The proposed approach is capable to construct its own set of activation operators to be applied widely in both quantum and classical applications to overcome the linearity limitation of classical perceptron.

DOI: 10.1109/icosst.2015.7396419

Related papers

Autonomous Quantum Perceptron Neural Network

Alaa Sagheer, Mohammed Zidan

Recently, with the rapid development of technology, there are a lot of applications require to achieve low-cost learning. However the computational power of classical artificial neural networks, they are not capable to provide low-cost learning. In contrast, quantum neural networks may be representing a good computational alternate to classical neural network approaches, based on the computational power of quantum bit (qubit) over the classical bit. In this paper we present a new computational approach to the quantum perceptron neural network can achieve learning in low-cost computation. The proposed approach has only one neuron can construct self-adaptive activation operators capable to accomplish the learning process in a limited number of iterations and, thereby, reduce the overall computational cost. The proposed approach is capable to construct its own set of activation operators to be applied widely in both quantum and classical applications to overcome the linearity limitation of classical perceptron. The computational power of the proposed approach is illustrated via solving variety of problems where promising and comparable results are given.

arXiv:1312.4149Dec 15, 201317 citations

Self-Organizing Quantum Neural Networks for Optimal Resource Allocation

Jincheng Zhang

This paper investigates the application of self-organizing quantum neural networks (SQNNs) to the problem of optimal resource allocation, a core challenge across diverse domains including finance, logistics, and telecommunications. Traditional classical neural networks frequently struggle to achieve optimal solutions when faced with complex constraints and dynamic environments. The central hypothesis of this work is that leveraging quantum computation through SQNNs, specifically utilizing qubit representations of resource states and exploiting entanglement, can significantly enhance the exploration of the solution space and lead to near-optimal resource allocation decisions. We propose a novel SQNN architecture designed to address this challenge. The architecture incorporates layers of quantum neurons that dynamically adjust their connectivity based on the input data, mimicking the self-organizing properties observed in biological neural networks. We present a theoretical framework outlining the key components of the SQNN and detail the mathematical formulation of the resource allocation problem being addressed. The core of the model is expressed as follows: Let *N* be the number of resources to be allocated. Let *K* be the number of potential allocation options for each resource. Let *xi* represent the allocation decision for resource *i*, where *xi* ∈ {1, 2, ..., *K*}. The objective is to minimize the cost function *C(x)*, which is defined as: *C(x) = ∑i=1N *Ci(xi)* where *Ci(xi)* represents the cost associated with resource *i* given the allocation *xi*. This cost function is subject to constraints *G(x) ≤ 0*, where *G* is a vector of constraints representing factors like capacity limits, demand requirements, and regulatory restrictions. The SQNN learns to approximate the optimal solution *x* that minimizes *C(x)* subject to the constraints *G(x) ≤ 0*. The network's self-organizing capability is achieved through a modified backpropagation algorithm adapted for quantum systems, incorporating quantum measurement and entangling operations to refine the network's internal state and improve its ability to represent and optimize the resource allocation problem. The efficacy of the SQNN is evaluated through simulations, demonstrating its potential to outperform classical neural networks in complex resource allocation scenarios.

Sep 2, 20260 citations

Quantum Neural Networks: Adaptive Activation for Enhanced Efficiency

Jincheng Zhang

Quantum Neural Networks (QNNs) represent a paradigm shift in machine learning, leveraging the unique properties of quantum systems to potentially surpass classical neural networks. However, the inherent complexity of quantum systems presents significant challenges in designing efficient and adaptable architectures. This paper explores the integration of adaptive activation functions into QNNs to address this challenge. We propose a novel mechanism for dynamically adjusting activation function parameters, fostering increased efficiency and improved model performance. The core of our work lies in a system that employs a feedback loop, iteratively refining the activation function based on the network's internal state and the task at hand. This adaptive process significantly reduces computational costs compared to static activation functions. We demonstrate the effectiveness of this approach through simulations and preliminary experiments, showcasing enhanced performance in a targeted task. The resulting QNN exhibits superior results in terms of accuracy and speed, highlighting the potential of this novel activation mechanism.

Sep 2, 20260 citations

Adaptive Neuron Connection for Quantum Neural Networks

Jincheng Zhang

Quantum neural networks (QNNs) hold immense promise for revolutionizing artificial intelligence, offering the potential for enhanced learning and complex pattern recognition. However, training QNNs often requires significant computational resources and time, hindering their widespread adoption. This paper introduces an innovative approach to QNNs – the Adaptive Neuron Connection (ANC) – designed to address this challenge by implementing a dynamic adjustment mechanism for neural neuron connections. This system leverages the inherent adaptability of quantum systems to dynamically adjust connection weights based on input signal variations, thereby reducing computational burden and improving model performance. We detail the architecture of the ANC, its operational principles, and preliminary experimental results demonstrating its effectiveness in several benchmark datasets. The core of this design lies in a novel dynamic weight adjustment algorithm that ensures optimal network performance across a wide range of input conditions. This work provides a new framework for QNNs, offering a pathway towards more efficient and scalable learning.

Sep 2, 20260 citations

Quantum Neural Networks with Adaptive Topological Structures Learning

Jincheng Zhang

This paper presents a novel approach to designing and implementing quantum neural networks (QNNs) capable of adapting their topological structures through a learning process. The core idea is to leverage reinforcement learning (RL) to guide the QNN's evolution, enabling it to dynamically optimize its architecture for specific tasks. Traditional QNNs typically employ fixed, pre-defined topologies, limiting their flexibility and potential performance. This work introduces a framework where the QNN autonomously learns and adjusts its topology, representing a significant advancement in QNN development. We detail the theoretical foundations, the RL algorithm employed, and the overall learning process. The system's ability to adapt to varying input data and computational demands is demonstrated, showcasing the potential of self-organizing QNNs for complex problems. The system's performance is evaluated using synthetic benchmarks, demonstrating the efficacy of the adaptive topological structure learning method. This research contributes to the burgeoning field of adaptive quantum computing, paving the way for more robust and efficient QNN designs. ---

Aug 28, 20260 citations

STOCK PRICE PREDICTION USING QUANTUM NEURAL NETWORK

R.P Mahajan

Quantum Neural Network (QNN) can improve upon the inadequacies of the classical neural network (CNN). The CNN requires a huge memory and needs more computational power. A new field of computation is emerging which integrates quantum computation with CNN. A quantum inspired hybrid model of quantum neurons and classical neurons is proposed. This paper details an approach, perhaps the first attempt; towards stock price prediction using this concept is evolved. The stock price prediction initiates the use of QNN in financial engineering applications

Journal of Global Research in Computer SciencesDec 9, 20101 citation