摘要 :
This work presents the region-based quantum evolutionary algorithm (RQEA) for solving numerical optimization problems. In the proposed algorithm, the feasible solution space is decomposed into regions in terms of quantum represent...
展开
This work presents the region-based quantum evolutionary algorithm (RQEA) for solving numerical optimization problems. In the proposed algorithm, the feasible solution space is decomposed into regions in terms of quantum representation. As the search progresses from one generation to the next, the quantum bits evolve gradually, increasing the probability of selecting regions that yield good fitness values. Through the inherent probabilistic mechanism, the RQEA initially behaves as a global search algorithm and gradually evolves into a local search algorithm, resulting in a good balance between exploration and exploitation. The RQEA is applied to a series of numerical optimization problems. The experiments show that the results obtained by the RQEA are better than those obtained using state-of-the-art QEA and DEahcSPX.
收起
摘要 :
? 2023Quantum neural network (QNN) is a neural network model based on the principles of quantum mechanics. The advantages of faster computing speed, higher memory capacity, smaller network size and elimination of catastrophic amne...
展开
? 2023Quantum neural network (QNN) is a neural network model based on the principles of quantum mechanics. The advantages of faster computing speed, higher memory capacity, smaller network size and elimination of catastrophic amnesia make it a new idea to solve the problem of training massive data that is difficult for classical neural networks. However, the quantum circuit of QNN are artificially designed with high circuit complexity and low precision in classification tasks. In this paper, a neural architecture search method EQNAS is proposed to improve QNN. First, initializing the quantum population after image quantum encoding. The next step is observing the quantum population and evaluating the fitness. The last is updating the quantum population. Quantum rotation gate update, quantum circuit construction and entirety interference crossover are specific operations. The last two steps need to be carried out iteratively until a satisfactory fitness is achieved. After a lot of experiments on the searched quantum neural networks, the feasibility and effectiveness of the algorithm proposed in this paper are proved, and the searched QNN is obviously better than the original algorithm. The classification accuracy on the mnist dataset and the warship dataset not only increased by 5.31% and 4.52%, respectively, but also reduced the parameters by 21.88% and 31.25% respectively. Code will be available at https://gitee.com/Pcyslist/models/tree/master/research/cv/EQNAS, and https://github.com/Pcyslist/EQNAS.
收起
摘要 :
In this paper, a quantum convolutional neural network (CNN) architecture is proposed to find the optimal number of convolutional layers. Since quantum bits use probability to represent binary information, the quantum CNN does not ...
展开
In this paper, a quantum convolutional neural network (CNN) architecture is proposed to find the optimal number of convolutional layers. Since quantum bits use probability to represent binary information, the quantum CNN does not represent the actual network, but the probability of existence of each convolutional layer, thus achieving the aim of training weights and optimising the number of convolutional layers at the same time. In the simulation part, CIFAR-10 (including 50k training images and 10k test images in 10 classes) is used to train VGG-19 and 20-layer, 32-layer, 44-layer and 56-layer CNN networks, and compare the difference between the optimal and non-optimal convolutional layer networks. The simulation results show that without optimisation, the accuracy of the test data drops from approximately 90% to about 80% as the number of network layers increases to 56 layers. However, the CNN with optimisation made it possible to maintain the test accuracy at more than 90%, and the number of network parameters could be reduced by nearly half or more. This shows that the proposed method can not only improve the network performance degradation caused by too many hidden convolutional layers, but also greatly reduce the use of the network's computing resources.
收起
摘要 :
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In ...
展开
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In this work a quantum inspired evolutionary algorithms, so-called Quantum evolutionary algorithm (QEA) [1], are utilized for optimal design of one gable frame and a multi-span frame in five alternatives with tapered members. In order to optimize the frames, the design is performed using the AISC specifications for stress, displacement and stability constraints. The design constraints and weight of the gable and multi-span frames are computed from the cross-section of members. These optimum weights are obtained using aforementioned optimization algorithm considering the cross-section of members and design constraints as optimization variables and constraints, respectively. A comparative study of the QEA and some recently developed methods from literature is also performed to illustrate the performance of the utilized optimization algorithm and its featuring. Furthermore, optimal design of a multi-span frame is compared with the solution of other methods including the same conditions and constraints. This study indicates the power of QEA in exploring and exploitation due the search space with using Q-gate and binary code for individual representation and updating. Binary code helps the QEA to find optimal solution even with minimum number of Q-bit individuals. High speed of this method is because of such a feature.
收起
摘要 :
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In ...
展开
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In this work a quantum inspired evolutionary algorithms, so-called Quantum evolutionary algorithm (QEA) [1], are utilized for optimal design of one gable frame and a multi-span frame in five alternatives with tapered members. In order to optimize the frames, the design is performed using the AISC specifications for stress, displacement and stability constraints. The design constraints and weight of the gable and multi-span frames are computed from the cross-section of members. These optimum weights are obtained using aforementioned optimization algorithm considering the cross-section of members and design constraints as optimization variables and constraints, respectively. A comparative study of the QEA and some recently developed methods from literature is also performed to illustrate the performance of the utilized optimization algorithm and its featuring. Furthermore, optimal design of a multi-span frame is compared with the solution of other methods including the same conditions and constraints. This study indicates the power of QEA in exploring and exploitation due the search space with using Q-gate and binary code for individual representation and updating. Binary code helps the QEA to find optimal solution even with minimum number of Q-bit individuals. High speed of this method is because of such a feature.
收起
摘要 :
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In ...
展开
The weight and shape of the gable and multi-span frames (mono and two-span pitched roof) with tapered members, as a familiar group of the pitched roof frames, are highly dependent on the properties of the member cross-section. In this work a quantum inspired evolutionary algorithms, so-called Quantum evolutionary algorithm (QEA) [1], are utilized for optimal design of one gable frame and a multi-span frame in five alternatives with tapered members. In order to optimize the frames, the design is performed using the AISC speci?cations for stress, displacement and stability constraints. The design constraints and weight of the gable and multi-span frames are computed from the cross-section of members. These optimum weights are obtained using aforementioned optimization algorithm considering the cross-section of members and design constraints as optimization variables and constraints, respectively. A comparative study of the QEA and some recently developed methods from literature is also performed to illustrate the performance of the utilized optimization algorithm and its featuring. Furthermore, optimal design of a multi-span frame is compared with the solution of other methods including the same conditions and constraints. This study indicates the power of QEA in exploring and exploitation due the search space with using Q-gate and binary code for individual representation and updating. Binary code helps the QEA to find optimal solution even with minimum number of Q-bit individuals. High speed of this method is because of such a feature.
收起
摘要 :
The quantum-inspired evolutionary algorithm (QEA) and QEA with a pair-swap strategy (QEAPS) have quantum-inspired individuals, where each gene is represented by a quantum bit (qubit). QEA and QEAPS iterate the evolution using the ...
展开
The quantum-inspired evolutionary algorithm (QEA) and QEA with a pair-swap strategy (QEAPS) have quantum-inspired individuals, where each gene is represented by a quantum bit (qubit). QEA and QEAPS iterate the evolution using the unitary transformation of probability amplitudes in each qubit, and can automatically shift the evolution from a global search to a local search. Here, the convergence speed depends on the rotation angle of each qubit toward either the |0? or |1? state vector, and the probability amplitude diverges or the population is likely to fall into a local solution if the rotation angle is too large. If the rotation angle is too small, the convergence speed may become low and the search performance will degrade. In this study, we introduce nonuniform convergence speeds into the quantum-inspired individuals and regard the convergence speed as the individual feature (individuality) of each quantum-inspired individual. Introducing the proposed individuality can eliminate the cumbersome process required to design a rotation angle while ensuring the quality of the obtained solution.
收起
摘要 :
Quantum-inspired evolutionary algorithm (QEA) has proved to be an effective method to design neural networks with few connections and high classification performance. When a quantum-inspired evolutionary neural network (QENN) conv...
展开
Quantum-inspired evolutionary algorithm (QEA) has proved to be an effective method to design neural networks with few connections and high classification performance. When a quantum-inspired evolutionary neural network (QENN) converges in the training phase, subsequent training is fruitless and time-wasting. Therefore, it is important to control the number of generations of QENN. The analysis on the convergence property of quantum bit evolution can contribute to designing a safe termination criterion that can always be reached. This paper proposes an appropriate termination criterion based on the average convergence rate (ACR). Experiments on classification tasks are conducted to demonstrate the effectiveness of our method. The results show that the termination criterion based on ACR can duly stop the training process of QENN and overcome the limitations of the termination criterion based on the probability of generating the best solution (PBS). (C) 2017 Elsevier B.V. All rights reserved.
收起
摘要 :
The quantum-inspired evolutionary algorithm (QEA) and QEA with a pair-swap strategy (QEAPS), where each gene is represented by a quantum bit (qubit) in both algorithms, have shown superior search performance to the classical genet...
展开
The quantum-inspired evolutionary algorithm (QEA) and QEA with a pair-swap strategy (QEAPS), where each gene is represented by a quantum bit (qubit) in both algorithms, have shown superior search performance to the classical genetic algorithm in the 0-1 knapsack problem. Also, from experimental results for the integer knapsack problem, a novel integer-type gene-coding method that can obtain an integer value as an observation result by assigning multiple qubits in a gene locus has shown superior search performance to the conventional binary-type gene-coding method. However, the integer-type gene-coding method cannot deal with permutations simply. Therefore, we have proposed two interpretation methods that can deal with permutations in order to expand the gene-coding method based on the qubit representation. From the results of a computer experiment using the proposed interpretation methods in the traveling salesman problem, we have clarified that the two proposed interpretation methods can search for the optimal solution, even with the gene-coding method based on the qubit representation. Moreover, there are suitable rotation angles for discovering the optimal solution that depend on the algorithm.
收起
摘要 :
The quantum-inspired evolutionary algorithm (QEA) is one of the evolutionary algorithms incorporating principles of quantum computation. In QEA, each gene is represented by a quantum bit (qubit), and the quantum superposition stat...
展开
The quantum-inspired evolutionary algorithm (QEA) is one of the evolutionary algorithms incorporating principles of quantum computation. In QEA, each gene is represented by a quantum bit (qubit), and the quantum superposition state is imitated. QEA can effectively shift from a global search to a local search. Han, et al. showed that QEA has superior search performance to a genetic algorithm (GA) in the 0-1 knapsack problem (0-1KP). Nakayama, et al. proposed a simpler algorithm that is referred to as QEA based on pair swap (QEAPS). QEAPS requires fewer parameters to be adjusted than QEA. Nakayama, et al. showed that QEAPS can find similar or even better quality solutions than QEA in 0-1KP. However, in QEA and QEAPS, each gene is represented by a qubit and both algorithms can only use a binary value as an observation result for a qubit. Therefore, Iimura, et al. proposed a novel integer-type gene-coding method that can obtain an integer value as an observation result by assigning multiple qubits in a gene locus. Moreover, they implemented the gene-coding method in both QEA and QEAPS and showed that it can search for similar or even better quality solutions in a shorter time than a conventional binary-type gene-coding method in the integer knapsack problem (IKP). However, the integer-type gene-coding method cannot deal with permutations simply.In order to expand the gene-coding method based on the qubit representation, Moriyama, et al. proposed two interpretation methods based on the integer-type gene-coding method that can deal with permutations. Also, they clarified that the two proposed interpretation methods can search for the optimal solution, even with the genecoding method based on the qubit representation. This paper proposes a new gene-coding method that can deal with permutations. The proposed method promises effect of improving a solution in permutation space, like the k-Opt method, and can search for the optimal solution of the traveling salesman problem (TSP) effectively. From experimental results for TSP, the discovery rate of the optimal solution using the proposed method is higher than using conventional method in many cases of QEA and QEAPS.
收起
原文获取