Application of fractional theory in quantum back propagation neural network

Dong, Yumin; Li, Xiang; Zhang, Jinlei; Li, Ziyi; Hou, Dong

doi:10.1002/mma.7550

Cited by 9 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e operation principle of the BP neural network derived above not only includes the three-layer neural network but also applies to the multilayer neural network. According to the weight adjustment formula between adjacent layers, the operation rules and adjustment speed of the whole neural network can be obtained [13].…”

Section: Bp Neural Networkmentioning

confidence: 99%

Big Data’s Analysis and Prediction Method of Art Education Based on the BP Neural Network

Zhu

2022

Security and Communication Networks

View full text Add to dashboard Cite

The traditional art education analysis and prediction are mainly based on the evaluation of human supervisors, and the evaluation results given by different evaluators vary greatly. The traditional analysis and prediction is difficult to reflect the objectivity and fairness of art education evaluation. This paper proposes a new idea of using the BP neural network model to analyze and forecast art education to improve the objectivity and impartiality of art education evaluation by big data. The work first constructed the art education evaluation index system covering the content of art education comprehensively and extensively. Then the BP neural network of art education analysis and prediction model was established. According to the content of art education evaluation system, the BP neural network’s input vector contains 30 evaluation indexes that affect art education, and its output vector is the art education evaluation results. The BP neural network with the structure of 30 × 10 × 1 was trained using the collected data. Finally, the work verified the scientificity of the evaluation model. The results of empirical analysis show that the established art education evaluation index system is reasonable and can reflect the artistic level of students, and the model of BP neural network has reliability in the analysis and prediction of art education big data and can objectively evaluate the level of art education.

show abstract

Section: Bp Neural Networkmentioning

confidence: 99%

Big Data’s Analysis and Prediction Method of Art Education Based on the BP Neural Network

Zhu

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…For this problem it is chosen by tuning of experiments 0.85 and 0.95. 46,47 TA B L E 4 Algorithm to receive packet in CQ-routing…”

Section: Dual Reinforcement Q-routing (Drq)mentioning

confidence: 99%

“…In the domain of machine learning and statistics, the learning rate (0.8, 0.1) is used as a tuning parameter for an optimization algorithm to determine the step size at each iteration during getting attained the minimum of a loss function. For this problem it is chosen by tuning of experiments 0.85 and 0.95 46,47 …”

Section: Proposed Model and Analysismentioning

confidence: 99%

Optimization of reinforcement routing for wireless mesh network using machine learning and high‐performance computing

Singh

Prakash

Singh

2022

Concurrency and Computation

View full text Add to dashboard Cite

In the modern world, wireless mesh networks (WMN) are widely used in Internet of Things (IoT) applications. It is a dynamic, infrastructure-less multihop network with mobility features. In WMN, to design an effective and strong routing protocol is a challenge. Conventional protocols for routing using a remote vector or link-state routing are not ideal for a wireless network. The shortest routing path is used with all current traditional routing protocols to pick a route with a minimum number of hops. The decisions must be done in real-time in high-traffic networks for the route selection and for the packets to be diversified into other routes. The routing protocols should adapt to the traffic conditions, that is, the network load changes and the route must be selected accordingly. The route may not be the shortest in number, but the best in terms of the actual time a packet requires to reach the target. The key objective of this research work is to design such an adaptive routing algorithm, while minimizing the delivery time and preventing the network from congestion. The rationale for this research work is to optimize adaptive routing protocol based on reinforcement learning, which efficiently delivers packets in the WMN. The experimental evaluation demonstrates that the obtained results significantly improve the system performance compared to the benchmark routing protocols. The Quality of Service (QoS) parameters such as packet delivery ratio (PDR), delay, and throughput metrics are used to assess the performance of the proposed technique using the NS-3 simulator.

show abstract

“…Besides, the researchers in [19] have considered Caputo's and Grünwald-Letnikov's fractional derivatives-based method for feedforward neural network for optimizing fractional-order delay optimum control problems. Another reported work in [20] has used Grünwald-Letnikov's derivative function as a learning algorithm and fractional calculus to reduce convergence error and speed. e singlepoint search algorithm reported in [21] has made an efficient global learning machine to determine the optimal search path.…”

Section: Introductionmentioning

confidence: 99%

Fractional Rectified Linear Unit Activation Function and Its Variants

Job

Bhateja

Gupta

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper focuses on deriving and validating the fractional-order form of rectified linear unit activation function and its linear and nonlinear variants. The linear variants include the leaky and parametric, whereas the nonlinear variants include the exponential, sigmoid-weighted, and Gaussian error functions. Besides, a standard formula has been created and used while developing the fractional form of linear variants. Moreover, different expansion series such as Maclaurin and Taylor have been used while designing the fractional version of nonlinear variants. A simulation study has been conducted to validate the performance of all the developed fractional activation functions utilizing a single and multilayer neural network model and to compare them with their conventional counterparts. In this simulation study, a neural network model has been created to predict the system-generated power of a Texas wind turbine. The performance has been evaluated by varying the activation function in the hidden and output layers with the developed functions for single and multilayer networks.

show abstract

Application of fractional theory in quantum back propagation neural network

Cited by 9 publications

References 27 publications

Big Data’s Analysis and Prediction Method of Art Education Based on the BP Neural Network

Big Data’s Analysis and Prediction Method of Art Education Based on the BP Neural Network

Optimization of reinforcement routing for wireless mesh network using machine learning and high‐performance computing

Fractional Rectified Linear Unit Activation Function and Its Variants

Contact Info

Product

Resources

About