Qubit neural network and its learning efficiency

Kouda, Noriaki; Matsui, Nobuyuki; Nishimura, Haruhiko; Peper, Ferdinand

doi:10.1007/s00521-004-0446-8

Cited by 114 publications

(60 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, in 1995, quantum inspired neural nets [3] was proposed by Narayanan et al In 2000, Ventura et al introduced quantum associative memory [4] based on the Grover's quantum search algorithm and entangled neural network [5,6] was presented by Li Wei-Gang. In 2005, Noriaki Kouda et al introduced qubit neural networks [7][8][9][10]. But these QNNs haven't obvious network weight, also haven't the weight learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Quantum M-P Neural Network

Zhou

Qiu-lin

2007

Int J Theor Phys

View full text Add to dashboard Cite

Quantum Neural Network (QNN) is a young and outlying science built upon the combination of classical neural network and quantum computing. Making use of quantum linear superposition, this paper presents a quantum M-P neural network based on the analysis of the conventional M-P neural network. Moreover, the working principle of this proposed network and its corresponding weight updating algorithm are expatiated in the two cases of input state being in the orthogonal and non-orthogonal basic set, respectively. In addition, this paper not only validates that this quantum M-P network can realize some network functions, such as "XOR", but also verifies the feasibility and validity of its weight learning algorithm by some simple examples.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantum M-P Neural Network

Zhou

Qiu-lin

2007

Int J Theor Phys

View full text Add to dashboard Cite

show abstract

“…Here we proposed and tested systems operating only in the classical regime, but there are no real limits to their use as quantum devices. Some authors suggest the possibility to introduce quantum logic in ANNs in order to extend their capabilities, similarly to what happens with the introduction of quantum computing [21,22]. In this direction, our scheme could be suitable for the real implementation of a possible quantum ANN.…”

Section: Experimental Setup Results and Discussionmentioning

confidence: 87%

Artificial neural network based on SQUIDs: demonstration of network training and operation

Chiarello

Carelli

Castellano

et al. 2013

Supercond. Sci. Technol.

View full text Add to dashboard Cite

Abstract. We propose a scheme for the realization of artificial neural networks based on Superconducting Quantum Interference Devices (SQUIDs). In order to demonstrate the operation of this scheme we designed and successfully tested a small network that implements a XOR gate and is trained by means of examples. The proposed scheme can be particularly convenient as support for superconducting applications such as detectors for astrophysics, high energy experiments, medicine imaging and so on. Artificial Neural NetworksArtificial Neural Networks (ANN) are a computing paradigm inspired by biological neural systems [1,2]. They are particularly effective in specific tasks such as pattern recognition, data mining, regression and analysis of series, classification, filtering and so on. An important characteristic of ANN is their capability to learn and to be trained in order to perform some required task. The training can be done once and for all during an initial preparatory phase (which can also be the design phase) if the network is used only for recurrent tasks, or it is possible to have a network that can learn during its use, in order to adapt itself to a changing environment. ANN can be realized in many different ways according to the needs of specific applications: for example they can be simulated by computer programs, or implemented by discrete electronic circuits, by microcontrollers, DSPs, ASICs and so on [3,4]. Unconventional electronics can also be used for this task, for example there are different proposals based on the use of superconducting electronics [5][6][7][8]. Superconducting electronics allows computing speeds not possible with conventional semiconductor electronics (with clocks of the order of hundreds of Gigahertz) [9][10][11], but its drawback is the necessity to use cryogenic systems, with relative costs and request of competences. However there are different examples of important existing applications based on low temperatures and superconductivity (astrophysical detectors, medical imaging, high energy physics, quantum communication and computing, ultra low noise electronics, metrology and so on) where the introduction of a superconducting electronics is not cause of extra cost, but rather it could provide a natural interface between the superconducting system and the room temperature electronics, performing preliminary tasks such as multiplexing, pre-analysis and triggering [12][13][14][15]. In many cases the availability of a fast superconducting ANN close to the system could be a very useful and desirable tool.In the present work we consider a simple and flexible scheme for the realization of ANNs with SQUIDs (Superconducting Quantum Interference Devices), a widely used class of superconducting devices characterized by outstanding performances as ultrasensitive magnetometers and low noise amplifiers [16][17][18]. In order to prove the operation of the proposed scheme we realized and tested a

show abstract

“…Such modification leads to variate of neural network paradigms such as polynomial neural network [233,244], where the nodes are designed to as a polynomial function based on inputs to the nodes. Similarly, the nodes of a GMDH neural network is designed as an Ivakhnenko polynomial [245]; the nodes of a complex value neural network or multivalued neural network is designed with a complex value activation functions [234]; the node of spiking neural networks has specific behavior, in which a node signal is propagated to another node only if the intrinsic quality of neural activation value is above a defined threshold [246]; the nodes of fuzzy neural network paradigm is designed using the concepts of fuzzy theory [247]; the node and the architecture of the Quantum neural network are inspired by the quantum computing [248][249][250][251]. In all such methods, metaheuristics have a significant role in the optimization.…”

Section: Node Optimizationmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

441

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract

Qubit neural network and its learning efficiency

Cited by 114 publications

References 15 publications

Quantum M-P Neural Network

Quantum M-P Neural Network

Artificial neural network based on SQUIDs: demonstration of network training and operation

Metaheuristic design of feedforward neural networks: A review of two decades of research

Contact Info

Product

Resources

About