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

arXiv:1609.05884 · Quanta

A Quantum Implementation Model for Artificial Neural Networks

Ammar Daskin

Published Feb 20, 2018• 6 citations
arXivHTMLPDF

Abstract

The learning process for multilayered neural networks with many nodes makes heavy demands on computational resources. In some neural network models, the learning formulas, such as the Widrow–Hoff formula, do not change the eigenvectors of the weight matrix while flatting the eigenvalues. In infinity, these iterative formulas result in terms formed by the principal components of the weight matrix, namely, the eigenvectors corresponding to the non-zero eigenvalues. In quantum computing, the phase estimation algorithm is known to provide speedups over the conventional algorithms for the eigenvalue-related problems. Combining the quantum amplitude amplification with the phase estimation algorithm, a quantum implementation model for artificial neural networks using the Widrow–Hoff learning rule is presented. The complexity of the model is found to be linear in the size of the weight matrix. This provides a quadratic improvement over the classical algorithms. Quanta 2018; 7: 7–18.

DOI
10.12743/quanta.v7i1.65

Related papers

An artificial neuron implemented on an actual quantum processor

Francesco Tacchino, Chiara Macchiavello, Dario Gerace +1 more

Abstract Artificial neural networks are the heart of machine learning algorithms and artificial intelligence. Historically, the simplest implementation of an artificial neuron traces back to the classical Rosenblatt’s “perceptron”, but its long term practical applications may be hindered by the fast scaling up of computational complexity, especially relevant for the training of multilayered perceptron networks. Here we introduce a quantum information-based algorithm implementing the quantum computer version of a binary-valued perceptron, which shows exponential advantage in storage resources over alternative realizations. We experimentally test a few qubits version of this model on an actual small-scale quantum processor, which gives answers consistent with the expected results. We show that this quantum model of a perceptron can be trained in a hybrid quantum-classical scheme employing a modified version of the perceptron update rule and used as an elementary nonlinear classifier of simple patterns, as a first step towards practical quantum neural networks efficiently implemented on near-term quantum processing hardware.

arXiv:1811.02266•npj Quantum Information•Mar 29, 2019•278 citations

A Quantum Model for Multilayer Perceptron

Changpeng Shao

Multilayer perceptron is the most common used class of feed-forward artificial neural network. It contains many applications in diverse fields such as speech recognition, image recognition, and machine translation software. To cater for the fast development of quantum machine learning, in this paper, we propose a new model to study multilayer perceptron in quantum computer. This contains the tasks to prepare the quantum state of the output signal in each layer and to establish the quantum version of learning algorithm about the weights in each layer. We will show that the corresponding quantum versions can achieve at least quadratic speedup or even exponential speedup over the classical algorithms. This provide us an efficient method to study multilayer perceptron and its applications in machine learning in quantum computer. Finally, as an inspiration, an exponential fast learning algorithm (based on Hebb's learning rule) of Hopfield network will be proposed.

arXiv:1808.10561•Aug 31, 2018•14 citations

Quantum Neuron: an elementary building block for machine learning on quantum computers

Yudong Cao, Gian Giacomo Guerreschi, Alán Aspuru‐Guzik

Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.

arXiv:1711.11240•Nov 30, 2017•113 citations

Implementing Any Nonlinear Quantum Neuron

Fernando M. de Paula Neto, Teresa B. Ludermir, Wilson Rosa de Oliveira +1 more

The ability of artificial neural networks (ANNs) to adapt to input data and perform generalizations is intimately connected to the use of nonlinear activation and propagation functions. Quantum versions of ANN have been proposed to take advantage of the possible supremacy of quantum over classical computing. To date, all proposals faced the difficulty of implementing nonlinear activation functions since quantum operators are linear. This brief presents an architecture to simulate the computation of an arbitrary nonlinear function as a quantum circuit. This computation is performed on the phase of an adequately designed quantum state, and quantum phase estimation recovers the result, given a fixed precision, in a circuit with linear complexity in function of ANN input size.

IEEE Transactions on Neural Networks and Learning Systems•Sep 25, 2019•31 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

Quantum phase estimation based algorithms for machine learning

Oumayma Ouedrhiri, Oumayma Banouar, Salah El Hadaj +1 more

Quantum computing is certainly one of the greatest advances in the computer science field. Thanks to the parallelism and entanglement properties, it has proved to offer several advantages compared to the classical algorithms especially in the great reduction of the processing time. Quantum phase estimation (QPE) is one of the most important algorithms for quantum computing. It is known as the eigenvalue finding module for unitary operators. The Fourier transform is the key to this procedure. It has been researched and used to solve many problems such as the order finding problem, and the factoring problem. It was also applied for quantum sampling algorithms and the calculation of the eigenvalues of unitary matrices. In this paper, we study three important quantum algorithms for machine learning that use the QPE algorithm as a subroutine: the quantum principal components analysis (PCA) for data visualization, the Harrow-Hassidim-Lloyd (HHL) algorithm for solving linear systems, and the quantum singular value thresholding (SVT) for matrix completion in recommender systems. We also discuss the advantages and limits of such algorithms compared to their classical versions. Then we discuss potential ways of amelioration of such algorithms, and end with a proposed approach for further improvement.

International Informatics and Software Engineering Conference (IISEC)•Dec 16, 2021•3 citations
The learning process for multilayered neural networks with many nodes makes heavy demands on computational resources. In some neural network models, the learning formulas, such as the Widrow–Hoff formula, do not change the eigenvectors of the weight matrix while flatting the eigenvalues. In infinity, these iterative formulas result in terms formed by the principal components of the weight matrix, namely, the eigenvectors corresponding to the non-zero eigenvalues. In quantum computing, the phase estimation algorithm is known to provide speedups over the conventional algorithms for the eigenvalue-related problems. Combining the quantum amplitude amplification with the phase estimation algorithm, a quantum implementation model for artificial neural networks using the Widrow–Hoff learning rule is presented. The complexity of the model is found to be linear in the size of the weight matrix. This provides a quadratic improvement over the classical algorithms. Quanta 2018; 7: 7–18.
Abstract Artificial neural networks are the heart of machine learning algorithms and artificial intelligence. Historically, the simplest implementation of an artificial neuron traces back to the classical Rosenblatt’s “perceptron”, but its long term practical applications may be hindered by the fast scaling up of computational complexity, especially relevant for the training of multilayered perceptron networks. Here we introduce a quantum information-based algorithm implementing the quantum computer version of a binary-valued perceptron, which shows exponential advantage in storage resources over alternative realizations. We experimentally test a few qubits version of this model on an actual small-scale quantum processor, which gives answers consistent with the expected results. We show that this quantum model of a perceptron can be trained in a hybrid quantum-classical scheme employing a modified version of the perceptron update rule and used as an elementary nonlinear classifier of simple patterns, as a first step towards practical quantum neural networks efficiently implemented on near-term quantum processing hardware.
Multilayer perceptron is the most common used class of feed-forward artificial neural network. It contains many applications in diverse fields such as speech recognition, image recognition, and machine translation software. To cater for the fast development of quantum machine learning, in this paper, we propose a new model to study multilayer perceptron in quantum computer. This contains the tasks to prepare the quantum state of the output signal in each layer and to establish the quantum version of learning algorithm about the weights in each layer. We will show that the corresponding quantum versions can achieve at least quadratic speedup or even exponential speedup over the classical algorithms. This provide us an efficient method to study multilayer perceptron and its applications in machine learning in quantum computer. Finally, as an inspiration, an exponential fast learning algorithm (based on Hebb's learning rule) of Hopfield network will be proposed.
Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.
The ability of artificial neural networks (ANNs) to adapt to input data and perform generalizations is intimately connected to the use of nonlinear activation and propagation functions. Quantum versions of ANN have been proposed to take advantage of the possible supremacy of quantum over classical computing. To date, all proposals faced the difficulty of implementing nonlinear activation functions since quantum operators are linear. This brief presents an architecture to simulate the computation of an arbitrary nonlinear function as a quantum circuit. This computation is performed on the phase of an adequately designed quantum state, and quantum phase estimation recovers the result, given a fixed precision, in a circuit with linear complexity in function of ANN input size.
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.
Quantum computing is certainly one of the greatest advances in the computer science field. Thanks to the parallelism and entanglement properties, it has proved to offer several advantages compared to the classical algorithms especially in the great reduction of the processing time. Quantum phase estimation (QPE) is one of the most important algorithms for quantum computing. It is known as the eigenvalue finding module for unitary operators. The Fourier transform is the key to this procedure. It has been researched and used to solve many problems such as the order finding problem, and the factoring problem. It was also applied for quantum sampling algorithms and the calculation of the eigenvalues of unitary matrices. In this paper, we study three important quantum algorithms for machine learning that use the QPE algorithm as a subroutine: the quantum principal components analysis (PCA) for data visualization, the Harrow-Hassidim-Lloyd (HHL) algorithm for solving linear systems, and the quantum singular value thresholding (SVT) for matrix completion in recommender systems. We also discuss the advantages and limits of such algorithms compared to their classical versions. Then we discuss potential ways of amelioration of such algorithms, and end with a proposed approach for further improvement.