Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Joint Conference on Neural Networks (IJCNN)

Quantum generation of neural networks

H. De Garisi, Ravichandra Sriram, Zijun Zhang

Published Jun 22, 2004• 4 citations
Publisher

Abstract

This paper shows how the new field of quantum computing can be applied to the creation of neural network circuits. Quantum computing is capable of processing huge numbers of quantum states simultaneously, in parallel, ("quantum parallelism"). In theory, QC ought to be able to process all possible points in a 2/sup N/ search space (of N bit bit-strings). If N is large, 2/sup N/ is gigantic, making a systematic search with a classical computer impossible. This paper presents an extended example of a simple QC algorithm applied to the generation of neural network circuits.

DOI
10.1109/ijcnn.2003.1223974

Related papers

Creating Quantum Circuits for Training Perceptron Neural Networks on the Principles of Grover's Algorithm

C. B. Pronin, O. I. Maksimychev, Andrey Vladimirovich Ostroukh +2 more

This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems. Large scale neural networks can require significant computing resources for training purposes, therefore Grover’s quantum search algorithm could be used as a way to speed up this process, thanks to its ability of simultaneously processing multiple input values of a given function.

Systems of Signals Generating and Processing in the Field of on Board Communications•Mar 15, 2022•12 citations

Quantum Neural Networks: A New Frontier

Boyu Zhang

In recent years, there has been remarkable progress in improving the availability of resources and refining algorithms for quantum computing. Since the late 1980s, the scientific community has been fascinated by the idea of harnessing quantum phenomena to tackle computational problems. This article provides a comprehensive exploration of the foundational theories and practical applications of quantum neural networks (QNNs), highlighting their potential to transform machine learning through unique features like quantum parallelism and entanglement. It delves into various QNN architectures, such as quantum circuits and hybrid quantum-classical models, showcasing their effectiveness in handling intricate computational tasks more efficiently than traditional neural networks. Furthermore, the article examines the current challenges and future prospects in this rapidly advancing field, emphasizing the pivotal role of QNNs in driving forward research in both quantum computing and artificial intelligence. Quantum neural networks are poised to not only enhance computational capabilities but also pave the way for groundbreaking innovations in diverse technological domains.

Theoretical and Natural Science•Nov 1, 2024•5 citations

Parametric Synthesis of Computational Circuits for Complex Quantum Algorithms

C. B. Pronin, Andrey Vladimirovich Ostroukh

At the moment, quantum circuits are created mainly by manually placing logic elements on lines that symbolize quantum bits. The purpose of creating Quantum Circuit Synthesizer "Naginata" was due to the fact that even with a slight increase in the number of operations in a quantum algorithm, leads to the significant increase in size of the corresponding quantum circuit. This causes serious difficulties both in creating and debugging these quantum circuits. The purpose of our quantum synthesizer is enabling users an opportunity to implement quantum algorithms using higher-level commands. This is achieved by creating generic blocks for frequently used operations such as: the adder, multiplier, digital comparator (comparison operator), etc. Thus, the user could implement a quantum algorithm by using these generic blocks, and the quantum synthesizer would create a suitable circuit for this algorithm, in a format that is supported by the chosen quantum computation environment. This approach greatly simplifies the processes of development and debugging a quantum algorithm. The proposed approach for implementing quantum algorithms has a potential application in the field of machine learning, in this regard, we provided an example of creating a circuit for training a simple neural network. Neural networks have a significant impact on the technological development of the transport and road complex, and there is a potential for improving the reliability and efficiency of their learning process by utilizing quantum computation, through the introduction of quantum computing.

arXiv:2209.09903•Sep 20, 2022•0 citations

Quantum Computing to the Advantage of Neural Network

Aditya Maltare, Ishita Jain, Keshav Agrawal +1 more

Artificial neural networks (ANN) have been shown to be effective in various machine learning–based big data analytics challenges. An ANN can learn and generalize the intricate and irregular aspects of the input data. In the era of big data, colossal amounts of data come from various sources. It is anticipated that a point will be reached where even supercomputers will likely be overwhelmed by the enormous data. Due to the volume and scope of the huge data, training an ANN in this situation is a difficult process. To identify patterns and evaluate the data, a vast number of parameters must be employed and tuned in the network. Since a quantum computer may represent data in various ways utilizing qubits, quantum computing (QC) is emerging as a subject that offers a solution to this issue. It is possible to identify hidden patterns in data that are challenging for a classical computer to find by using qubits on quantum computers. As a result, the field of ANN has a wide range of potential applications. In this work, our main goal was to train an artificial neural network with qubits acting as its synthetic neurons. The simulation results demonstrate that, when compared to conventional ANN, our QC solution for ANN (QC ANN) is effective. For a binary classification job, the model that uses qubits as artificial neurons may learn the properties of data with fewer parameters. We employ a quantum simulator to demonstrate our experiment, and a conventional computer is used to optimize the quantum parameters used in the QC ANN.

Wiley eBooks•Oct 13, 2023•0 citations

Artificial neural network architecture selection in a quantum computer

Adenilton José da Silva

Miniaturisation of computers components is taking us from classical to quantum physics domain. Further reduction in computer components size eventually will lead to the development of computer systems whose components will be on such a small scale that quantum physics intrinsic properties must be taken into account. The expression quantum computation and a first formal model of a quantum computer were first employed in the eighties. With the discovery of a quantum algorithm for factoring exponentially faster than any known classical algorithm in 1997, quantum computing began to attract industry investments for the development of a quantum computer and the design of novel quantum algorithms. For instance, the development of learning algorithms for neural networks. Some artificial neural networks models can simulate an universal Turing machine, and together with learning capabilities have numerous applications in real life problems. One limitation of artificial neural networks is the lack of an efficient algorithm to determine its optimal architecture. The main objective of this work is to verify whether we can obtain some advantage with the use of quantum computation techniques in a neural network learning and architecture selection procedure. We propose a quantum neural network, named quantum perceptron over a field (QPF). QPF is a direct generalisation of a classical perceptron which addresses some drawbacks found in previous models for quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimises the neural network weights and architectures. SAL searches for the best architecture in a finite set of neural network architectures and neural networks parameters in linear time over the number of examples in the training set. SAL is the first quantum learning algorithm to determine neural network architectures in linear time. This speedup is obtained by the use of quantum parallelism and a non linear quantum operator.

•Jun 26, 2015•0 citations

Applying quantum search to automated test pattern generation for VLSI circuits

Sarbjeet Singh, Amardeep S. G. Singh

We present a quantum search algorithm for automated test pattern generation (ATPG) of combinatorial VLSI circuits. This problem can be viewed as an optimization problem because digital circuits can be modeled as a neural network and the problem become to minimize the energy function of this neural network. The solution of the equation gives us the test vector. Here specific aspects of quantum theory like superposition and quantum parallelism are applied to this problem. In quantum search algorithm this problem is viewed as a searching problem where the search function (also called oracle) f(x)=1 if the value of the energy function of the neural network is 0 otherwise f(x)=0. Quantum mechanics help us to search a group of items simultaneously from the search space rather than one item at a time. The algorithm is so efficient that it requires only, on average, roughly /spl radic/N (where N is the total number of vectors) searches to find the desired test vector, as opposed to a search in classical computing, which on average needs N/2 searches. A comparison is made between exhaustive, simulated annealing and quantum based search techniques. Experimental results show that the quantum search algorithms are more efficient than classical algorithms and can be applied with more efficiency on a quantum computer.

International Scientific and Practical Conference of Students, Post-graduates and Young Scientists: Modern Techniques and Technology (MTT)•Mar 1, 2004•4 citations
This paper shows how the new field of quantum computing can be applied to the creation of neural network circuits. Quantum computing is capable of processing huge numbers of quantum states simultaneously, in parallel, ("quantum parallelism"). In theory, QC ought to be able to process all possible points in a 2/sup N/ search space (of N bit bit-strings). If N is large, 2/sup N/ is gigantic, making a systematic search with a classical computer impossible. This paper presents an extended example of a simple QC algorithm applied to the generation of neural network circuits.
This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems. Large scale neural networks can require significant computing resources for training purposes, therefore Grover’s quantum search algorithm could be used as a way to speed up this process, thanks to its ability of simultaneously processing multiple input values of a given function.
In recent years, there has been remarkable progress in improving the availability of resources and refining algorithms for quantum computing. Since the late 1980s, the scientific community has been fascinated by the idea of harnessing quantum phenomena to tackle computational problems. This article provides a comprehensive exploration of the foundational theories and practical applications of quantum neural networks (QNNs), highlighting their potential to transform machine learning through unique features like quantum parallelism and entanglement. It delves into various QNN architectures, such as quantum circuits and hybrid quantum-classical models, showcasing their effectiveness in handling intricate computational tasks more efficiently than traditional neural networks. Furthermore, the article examines the current challenges and future prospects in this rapidly advancing field, emphasizing the pivotal role of QNNs in driving forward research in both quantum computing and artificial intelligence. Quantum neural networks are poised to not only enhance computational capabilities but also pave the way for groundbreaking innovations in diverse technological domains.
At the moment, quantum circuits are created mainly by manually placing logic elements on lines that symbolize quantum bits. The purpose of creating Quantum Circuit Synthesizer "Naginata" was due to the fact that even with a slight increase in the number of operations in a quantum algorithm, leads to the significant increase in size of the corresponding quantum circuit. This causes serious difficulties both in creating and debugging these quantum circuits. The purpose of our quantum synthesizer is enabling users an opportunity to implement quantum algorithms using higher-level commands. This is achieved by creating generic blocks for frequently used operations such as: the adder, multiplier, digital comparator (comparison operator), etc. Thus, the user could implement a quantum algorithm by using these generic blocks, and the quantum synthesizer would create a suitable circuit for this algorithm, in a format that is supported by the chosen quantum computation environment. This approach greatly simplifies the processes of development and debugging a quantum algorithm. The proposed approach for implementing quantum algorithms has a potential application in the field of machine learning, in this regard, we provided an example of creating a circuit for training a simple neural network. Neural networks have a significant impact on the technological development of the transport and road complex, and there is a potential for improving the reliability and efficiency of their learning process by utilizing quantum computation, through the introduction of quantum computing.
Artificial neural networks (ANN) have been shown to be effective in various machine learning–based big data analytics challenges. An ANN can learn and generalize the intricate and irregular aspects of the input data. In the era of big data, colossal amounts of data come from various sources. It is anticipated that a point will be reached where even supercomputers will likely be overwhelmed by the enormous data. Due to the volume and scope of the huge data, training an ANN in this situation is a difficult process. To identify patterns and evaluate the data, a vast number of parameters must be employed and tuned in the network. Since a quantum computer may represent data in various ways utilizing qubits, quantum computing (QC) is emerging as a subject that offers a solution to this issue. It is possible to identify hidden patterns in data that are challenging for a classical computer to find by using qubits on quantum computers. As a result, the field of ANN has a wide range of potential applications. In this work, our main goal was to train an artificial neural network with qubits acting as its synthetic neurons. The simulation results demonstrate that, when compared to conventional ANN, our QC solution for ANN (QC ANN) is effective. For a binary classification job, the model that uses qubits as artificial neurons may learn the properties of data with fewer parameters. We employ a quantum simulator to demonstrate our experiment, and a conventional computer is used to optimize the quantum parameters used in the QC ANN.
Miniaturisation of computers components is taking us from classical to quantum physics domain. Further reduction in computer components size eventually will lead to the development of computer systems whose components will be on such a small scale that quantum physics intrinsic properties must be taken into account. The expression quantum computation and a first formal model of a quantum computer were first employed in the eighties. With the discovery of a quantum algorithm for factoring exponentially faster than any known classical algorithm in 1997, quantum computing began to attract industry investments for the development of a quantum computer and the design of novel quantum algorithms. For instance, the development of learning algorithms for neural networks. Some artificial neural networks models can simulate an universal Turing machine, and together with learning capabilities have numerous applications in real life problems. One limitation of artificial neural networks is the lack of an efficient algorithm to determine its optimal architecture. The main objective of this work is to verify whether we can obtain some advantage with the use of quantum computation techniques in a neural network learning and architecture selection procedure. We propose a quantum neural network, named quantum perceptron over a field (QPF). QPF is a direct generalisation of a classical perceptron which addresses some drawbacks found in previous models for quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimises the neural network weights and architectures. SAL searches for the best architecture in a finite set of neural network architectures and neural networks parameters in linear time over the number of examples in the training set. SAL is the first quantum learning algorithm to determine neural network architectures in linear time. This speedup is obtained by the use of quantum parallelism and a non linear quantum operator.
We present a quantum search algorithm for automated test pattern generation (ATPG) of combinatorial VLSI circuits. This problem can be viewed as an optimization problem because digital circuits can be modeled as a neural network and the problem become to minimize the energy function of this neural network. The solution of the equation gives us the test vector. Here specific aspects of quantum theory like superposition and quantum parallelism are applied to this problem. In quantum search algorithm this problem is viewed as a searching problem where the search function (also called oracle) f(x)=1 if the value of the energy function of the neural network is 0 otherwise f(x)=0. Quantum mechanics help us to search a group of items simultaneously from the search space rather than one item at a time. The algorithm is so efficient that it requires only, on average, roughly /spl radic/N (where N is the total number of vectors) searches to find the desired test vector, as opposed to a search in classical computing, which on average needs N/2 searches. A comparison is made between exhaustive, simulated annealing and quantum based search techniques. Experimental results show that the quantum search algorithms are more efficient than classical algorithms and can be applied with more efficiency on a quantum computer.