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)

A Quantum Activation Function for Neural Networks: Proposal and Implementation

Saurabh Kumar, Siddharth Dangwal, Soumik Adhikary, Debanjan Bhowmik

Published Jul 18, 2021• 4 citations
Publisher

Abstract

A non-linear activation function is an integral component of neural network algorithms used for various tasks such as data classification and pattern recognition. In neu-romorphic/emerging-hardware-based implementations of neural network algorithms, the non-linear activation function is often implemented through dedicated analog electronics. This enables faster execution of the activation function during training and inference of neural networks compared to conventional digital implementation. Here, with a similar motivation, we propose a novel non-linear activation function that can be used in a neural network for data classification. Our activation function can be implemented by taking advantage of the inherent nonlinearity in qubit preparation and SU(2) operation in quantum mechanics. These operations are directly implementable on quantum hardware through single-qubit quantum gates as we show here. In addition, the SU(2) parameters are adjustable here making the activation function adaptable; we adjust the parameters through classical feedback like in a variational algorithm in quantum machine learning. Using our proposed quantum activation function, we report accurate classification using popular machine learning data sets like Fisher's Iris, Wisconsin's Breast Cancer (WBC), Abalone, and MNIST on three different platforms: simulations on a classical computer, simulations on a quantum simulation framework like Qiskit, and experimental implementation on quantum hardware (IBM-Q). Then we use a Bloch-sphere-based approach to intuitively explain how our proposed quantum activation function, with its adaptability, helps in data classification.

DOI
10.1109/ijcnn52387.2021.9533362

Related papers

NISQ-Friendly Non-Linear Activation Functions for Quantum Neural Networks

Sohrab Sajadimanesh, Jean Paul Latyr Faye, Ehsan Atoofian

The current generation of quantum computers calls for quantum algorithms that require a limited number of quantum gates and are resilient to noises. A suitable design strategy is variational circuits where parameters of circuits are determined through training, an approach that conforms with characteristics of machine learning applications. In this paper, we propose a low-depth and implementation-efficient non-linear activation function for quantum neural networks (QNNs). The building block of a quantum circuit is quantum gate which is a unitary operation. Thus, building a non-linear component out of quantum gates is challenging. While the majority of prior works used measurement as the source of non-linearity, this method has limited ability in classifying datasets. We propose a quantum circuit for the popular Rectified Linear Unit (ReLU) activation function. Our proposed circuit is based on low-cost quantum gates that can be synthesized into primitive gates in contemporary quantum computers. We exploit QNNs that rely on quantum rotation to define decision boundaries for classification problems. In addition, we use controlled quantum gates to detect correlation in data through entanglement of qubits. Our evaluations reveal that QNNs equipped with our proposed quantum ReLU perform well on standard benchmark datasets while requiring dramatically fewer number of epochs for training compared with classical neural networks. In addition, we run QNNs with different number of quantum layers on an IBM quantum computer and show that our proposed circuits are practical and generate meaningful results on real quantum computers.

IEEE International Conference on Networking, Architecture and Storage (NAS)•Oct 1, 2022•7 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, 2026•0 citations

Analog Quantum Variational Embedding Classifier

Rui Liang Yang, Samuel Bosch, Bobak T. Kiani +2 more

Quantum machine learning has the potential to provide powerful algorithms for artificial intelligence. The pursuit of quantum advantage in quantum machine learning is an active area of research. For current noisy intermediate-scale quantum computers, various quantum-classical hybrid algorithms have been proposed. One such previously proposed hybrid algorithm is a gate-based variational embedding classifier, which is composed of a classical neural network and a parameterized gate-based quantum circuit. We propose a quantum variational embedding classifier based on an analog quantum computer, where control signals vary continuously in time: our particular focus is an implementation using quantum annealers. In our algorithm, the classical data are transformed into the parameters of the time-varying Hamiltonian of the analog quantum computer by a linear transformation. The nonlinearity needed for a nonlinear classification problem is purely provided by the analog quantum computer through the nonlinear dependence of the final quantum state on the control parameters of the Hamiltonian. We perform numerical simulations that demonstrate the effectiveness of our algorithm for performing binary and multiclass classification on linearly inseparable datasets such as concentric circles and MNIST digits. Our classifier can reach accuracy comparable with that of the best classical classifiers. We find that the performance of our classifier can be increased by increasing the number of qubits, until the performance saturates and fluctuates. Moreover, the number of optimization parameters of our classifier scales linearly with the number of qubits. The increase of the number of training parameters when the size of our model increases is therefore not as fast as that of a neural network. Our algorithm presents the possibility of using current quantum annealers for solving practical machine-learning problems, and it could also be useful to explore quantum advantage in quantum machine learning.

arXiv:2211.02748•Physical Review Applied•May 5, 2023•11 citations

An Analytical Review of Quantum Neural Network Models and Relevant Research

Simantini Chakraborty, Tamal Das, Saurav Sutradhar +2 more

Quantum Machine Learning is gaining prominence with the advent of real quantum processors. The quantum analogue of one of the most important and popular model of machine learning, namely Artificial Neural Network is studied and reviewed here in this paper. Various approaches to design and implement a quantum neural network has been studied. Most of the works done in this field involved a translation of classical neural network components into the language of quantum physics. But direct translation cannot be a solution as not every classical component has a quantum analogue. Non-linear activation functions are good examples of it. Quantum operators need to be linear and therefore finding alternate solutions to activation functions is an active area of research. Nevertheless, its advantages over the classical models are profound. Quantum superposition gives exponential storage capacity to a quantum network. Quantum parallelism can be put to use and to train the network with multiple inputs in one go. Despite being a new field, many real world applications of a quantum neural network has also been theorised. These models, their advantages, applications and limitations has been discussed in this paper.

International Conference on Communication and Electronics Systems (ICCES)•Jun 1, 2020•20 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

Hybrid Quantum-Classical Neural Networks

Davis Arthur, Prasanna Date

Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers are soon expected to approach the physical limitations that will slow their performance improvements in the near future. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated IBM universal quantum computer and a state-of-the-art IBM universal quantum computer. On the simulated hardware, we observe that the hybrid neural network achieves around 10% higher classification accuracy and 20% better minimization of the cost function than an individual variational quantum circuit. On the quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 1, 2022•54 citations
A non-linear activation function is an integral component of neural network algorithms used for various tasks such as data classification and pattern recognition. In neu-romorphic/emerging-hardware-based implementations of neural network algorithms, the non-linear activation function is often implemented through dedicated analog electronics. This enables faster execution of the activation function during training and inference of neural networks compared to conventional digital implementation. Here, with a similar motivation, we propose a novel non-linear activation function that can be used in a neural network for data classification. Our activation function can be implemented by taking advantage of the inherent nonlinearity in qubit preparation and SU(2) operation in quantum mechanics. These operations are directly implementable on quantum hardware through single-qubit quantum gates as we show here. In addition, the SU(2) parameters are adjustable here making the activation function adaptable; we adjust the parameters through classical feedback like in a variational algorithm in quantum machine learning. Using our proposed quantum activation function, we report accurate classification using popular machine learning data sets like Fisher's Iris, Wisconsin's Breast Cancer (WBC), Abalone, and MNIST on three different platforms: simulations on a classical computer, simulations on a quantum simulation framework like Qiskit, and experimental implementation on quantum hardware (IBM-Q). Then we use a Bloch-sphere-based approach to intuitively explain how our proposed quantum activation function, with its adaptability, helps in data classification.
The current generation of quantum computers calls for quantum algorithms that require a limited number of quantum gates and are resilient to noises. A suitable design strategy is variational circuits where parameters of circuits are determined through training, an approach that conforms with characteristics of machine learning applications. In this paper, we propose a low-depth and implementation-efficient non-linear activation function for quantum neural networks (QNNs). The building block of a quantum circuit is quantum gate which is a unitary operation. Thus, building a non-linear component out of quantum gates is challenging. While the majority of prior works used measurement as the source of non-linearity, this method has limited ability in classifying datasets. We propose a quantum circuit for the popular Rectified Linear Unit (ReLU) activation function. Our proposed circuit is based on low-cost quantum gates that can be synthesized into primitive gates in contemporary quantum computers. We exploit QNNs that rely on quantum rotation to define decision boundaries for classification problems. In addition, we use controlled quantum gates to detect correlation in data through entanglement of qubits. Our evaluations reveal that QNNs equipped with our proposed quantum ReLU perform well on standard benchmark datasets while requiring dramatically fewer number of epochs for training compared with classical neural networks. In addition, we run QNNs with different number of quantum layers on an IBM quantum computer and show that our proposed circuits are practical and generate meaningful results on real quantum computers.
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.
Quantum machine learning has the potential to provide powerful algorithms for artificial intelligence. The pursuit of quantum advantage in quantum machine learning is an active area of research. For current noisy intermediate-scale quantum computers, various quantum-classical hybrid algorithms have been proposed. One such previously proposed hybrid algorithm is a gate-based variational embedding classifier, which is composed of a classical neural network and a parameterized gate-based quantum circuit. We propose a quantum variational embedding classifier based on an analog quantum computer, where control signals vary continuously in time: our particular focus is an implementation using quantum annealers. In our algorithm, the classical data are transformed into the parameters of the time-varying Hamiltonian of the analog quantum computer by a linear transformation. The nonlinearity needed for a nonlinear classification problem is purely provided by the analog quantum computer through the nonlinear dependence of the final quantum state on the control parameters of the Hamiltonian. We perform numerical simulations that demonstrate the effectiveness of our algorithm for performing binary and multiclass classification on linearly inseparable datasets such as concentric circles and MNIST digits. Our classifier can reach accuracy comparable with that of the best classical classifiers. We find that the performance of our classifier can be increased by increasing the number of qubits, until the performance saturates and fluctuates. Moreover, the number of optimization parameters of our classifier scales linearly with the number of qubits. The increase of the number of training parameters when the size of our model increases is therefore not as fast as that of a neural network. Our algorithm presents the possibility of using current quantum annealers for solving practical machine-learning problems, and it could also be useful to explore quantum advantage in quantum machine learning.
Quantum Machine Learning is gaining prominence with the advent of real quantum processors. The quantum analogue of one of the most important and popular model of machine learning, namely Artificial Neural Network is studied and reviewed here in this paper. Various approaches to design and implement a quantum neural network has been studied. Most of the works done in this field involved a translation of classical neural network components into the language of quantum physics. But direct translation cannot be a solution as not every classical component has a quantum analogue. Non-linear activation functions are good examples of it. Quantum operators need to be linear and therefore finding alternate solutions to activation functions is an active area of research. Nevertheless, its advantages over the classical models are profound. Quantum superposition gives exponential storage capacity to a quantum network. Quantum parallelism can be put to use and to train the network with multiple inputs in one go. Despite being a new field, many real world applications of a quantum neural network has also been theorised. These models, their advantages, applications and limitations has been discussed in this paper.
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.
Deep learning is one of the most successful and far-reaching strategies used in machine learning today. However, the scale and utility of neural networks is still greatly limited by the current hardware used to train them. These concerns have become increasingly pressing as conventional computers are soon expected to approach the physical limitations that will slow their performance improvements in the near future. For these reasons, scientists have begun to explore alternative computing platforms, like quantum computers, for training neural networks. In recent years, variational quantum circuits have emerged as one of the most successful approaches to quantum deep learning on noisy intermediate scale quantum devices. We propose a hybrid quantum-classical neural network architecture where each neuron is a variational quantum circuit. We empirically analyze the performance of this hybrid neural network on a series of binary classification data sets using a simulated IBM universal quantum computer and a state-of-the-art IBM universal quantum computer. On the simulated hardware, we observe that the hybrid neural network achieves around 10% higher classification accuracy and 20% better minimization of the cost function than an individual variational quantum circuit. On the quantum hardware, we observe that each model only performs well when the qubit and gate count is sufficiently small.