Laser Physics Letters

A novel quantum neural network based on multi-level activation function

Xu-Feng Niu, Wenping Ma

Published Jan 7, 2021• 16 citations

Abstract

Abstract Since the multi-level activation function quantum neural network (QNN) for pattern recognition was firstly proposed by Purushothaman and Karayiannis, more and more researches have been conducted on improving it. However, they all ignore that the QNN only uses multi-level activation function to simulate the concept of quantum superposition rather than really using quantum computing. In this paper, we propose a real QNN model based on multi-layer activation function. In addition, we present algorithms for updating weight parameters and quantum intervals, and also improve the learning algorithm for weight parameters using famous Levenberg–Marquardt algorithm. We also use the QNN for lie detection, and the simulation results of MATLAB prove that the performance of the model based on the corresponding algorithm are very strong.

DOI: 10.1088/1612-202x/abd23c

Related papers

Model of a quantum neural network based on a multilevel activation function

S.M. Gushansky, V.E. Buglov

This article proposes a model of a quantum neural network based on a multilevel activation function, which has high performance. This performance is achieved by combining such unique components as: the quantum weight vector, quantum activity values and the dot product operator. In addition, algorithms for learning weight parameters and quantum intervals are presented, in particular, the Levenberg-Marquardt algorithm is improved to improve the quality of the error back propagation method in the process of learning weight parameters, which will also reduce the likelihood of quantum errors.

Informatization and communicationJan 1, 20220 citations

Research on Quantum Neural Network and its Applications Based on Tanh Activation Function

Huifang Li

In this paper an improved quantum neural network(QNN) is presented based on multilevel activation function to solve the problems of precision inadequacy and low convergence rate of the BP neural network used in character recognition.Firstly,momentum term is used to updating the weights to accelerate the convergence rate of learning algorithm in QNN.Secondly,a linear superposition of hyperbolic tangent function is used as activation function of hidden unit in the new networks to classify pattern recognition problems that have uncertainty and overlapping data between two patterns.Finally,The experimental results for number,letter,and Chinese character recognition is provided and compared with both BP neural networks and the original Qnn.Results indicate that the improved Qnn not only takes great recognition rate,but also decreases the number of the training time comparing with the original one.The superiority is demonstrated by simulation.

Computer and Digital EngineeringJan 1, 20126 citations

Learning Algorithm and Application of Quantum Neural Networks with Quantum Weights

Dianbao Mu, Zunyou Guan, Hong Zhang

A novel neural networks model with quantum weights is present.Firstly, based on the information processing modes of biology neuron and quantum computing theory, a quantum neuron model is presented, which is composed of weighting, aggregating, activating, and inspiriting.Secondly the quantum neural networks model based on quantum neuron is constructed in which the input and the output are real vectors; the linked weight and the activation value are qubits.On the basic of the gradient descent algorithm, a learning algorithm of this model is proposed.It is shown that this algorithm is super-linearly convergent under certain conditions and can increase the probability of getting the global optimal solution.Finally, the availability of the model is illustrated in both convergence speed and convergence rate by two application examples of pattern recognition and function approximation.

International Journal of Computer Theory and EngineeringJan 1, 201327 citations

Research on Quantum Neural Networks and Its Convergence Property

Li-liang Ding, Li Chen

The training algorithm and the structure of quantum neural networks (QNN) that based on multilevel activation function are presented in this paper. Aiming at the influence of the activation function of output layer and the phenomenon of error saturation in the training process on the output values and convergence property, a linear superposition of arctangent function is introduced in as hide layer activation function, and error saturation prevention (ESP) function is constructed to improve the convergence property of QNN. The results of simulation program show that the convergence property is improved obviously.

International Conference on Natural Computation (ICNC)Jan 1, 20084 citations

Quantum activation functions for quantum neural networks

Marco Maronese, C. Destri, Enrico Prati

Abstract The field of artificial neural networks is expected to strongly benefit from recent developments of quantum computers. In particular, quantum machine learning, a class of quantum algorithms which exploit qubits for creating trainable neural networks, will provide more power to solve problems such as pattern recognition, clustering and machine learning in general. The building block of feed-forward neural networks consists of one layer of neurons connected to an output neuron that is activated according to an arbitrary activation function. The corresponding learning algorithm goes under the name of Rosenblatt perceptron. Quantum perceptrons with specific activation functions are known, but a general method to realize arbitrary activation functions on a quantum computer is still lacking. Here, we fill this gap with a quantum algorithm which is capable to approximate any analytic activation functions to any given order of its power series. Unlike previous proposals providing irreversible measurement–based and simplified activation functions, here we show how to approximate any analytic function to any required accuracy without the need to measure the states encoding the information. Thanks to the generality of this construction, any feed-forward neural network may acquire the universal approximation properties according to Hornik’s theorem. Our results recast the science of artificial neural networks in the architecture of gate-model quantum computers.

arXiv:2201.03700Quantum Information ProcessingMar 30, 202249 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