11,430 Hits in 8.4 sec

Evolutionary optimization of neural networks with heterogeneous computation: study and implementation

Jorge D. Fe, Ramón J. Aliaga, Rafael Gadea-Gironés
2015 Journal of Supercomputing  
In the optimization of Artificial Neural Networks (ANNs) via Evolutionary Algorithms (EAs) and the implementation of the necessary training for the objective function, there is often a trade-off between  ...  This paper presents, first of all, a study that shows the need of heterogeneous platform (CPU-GPU-FPGA) to accelerate the optimization of ANNs using genetic algorithms and, secondly, an implementation  ...  Acknowledgments The translation of this paper was funded by the Universitat Politècnica de València, Spain  ... 
doi:10.1007/s11227-015-1419-7 fatcat:y2opovhe5neobhnjdfmerz7yza

Evolvable Hardware for Generalized Neural Networks

Masahiro Murakawa, Shuji Yoshizawa, Isamu Kajitani, Tetsuya Higuchi
1997 International Joint Conference on Artificial Intelligence  
In our system, both the topology and the hidden layer node functions of a neural network mapped on the chips are dynamically changed using a genetic algorithm.  ...  Thus, the most desirable network topology and choice of node function (e.g. Gaussian or sigmoid) for a given application can be determined adaptively.  ...  Such approaches typically utilize a GA to evolve the optimal topology of an appropriate network, and then use back-propagation to train the weights.  ... 
dblp:conf/ijcai/MurakawaYKH97 fatcat:mhaznvbhxzddlpkh5vjev6nxra

The parallel genetic algorithm for construction of technological objects neural network models

V. S. Tynchenko, E. A. Petrovsky, V. V. Tynchenko
2016 2016 2nd International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)  
It is proposed to modify the standard multipopular parallel genetic algorithm adding its base topology dynamic adaptation.  ...  The parallel genetic algorithms implementation for neural networks models construction is discussed. The modification of this global optimization algorithm is proposed.  ...  GENETIC ALGORITHMS FOR ARTIFICIAL NEURAL NETWORK CONSTRUCTION In the genetic algorithm (GA), adapted to the training of neural networks, each individual of the population represents a complete set of neural  ... 
doi:10.1109/icieam.2016.7911573 fatcat:lhyj5lb3xjaobe54eumsi63adm

Improved Learning in Constructive Neural Networks for Pattern Classification using Genetic Algorithm

Mochitha Vijayan, S. S Sridhar, Vivia John
2017 Indian Journal of Science and Technology  
CoNN dispenses an optimal strategy in designing the structures of the multilayer perceptron networks, coupled with supervised algorithms for further learning.  ...  The proposed work also demonstrates the improvement of CoNN in terms of convergence, generalization accuracy, and space optimization.  ...  Instead of learning on a pre-fixed network topology, an algorithm which is constructive in nature learns the topology in a problem dependent way.  ... 
doi:10.17485/ijst/2017/v10i18/92674 fatcat:bri2a5dcgrgmvmvmcnmm4urija

Research on the Difficulty of Mobile Node Deployment's Self-Play in Wireless Ad Hoc Networks Based on Deep Reinforcement Learning

Huitao Wang, Ruopeng Yang, Changsheng Yin, Xiaofei Zou, Xuefeng Wang, KI-IL Kim
2021 Wireless Communications and Mobile Computing  
A deployment model of mobile nodes in wireless ad hoc networks based on the AlphaZero algorithm is designed.  ...  Deep reinforcement learning is one kind of machine learning algorithms which uses the maximum cumulative reward to learn the optimal strategy.  ...  Based on genetic algorithm, artificial bee colony algorithm, 2 Wireless Communications and Mobile Computing particle swarm algorithm, and other artificial intelligence network topology optimization algorithms  ... 
doi:10.1155/2021/4361650 fatcat:q74nrb7vm5fvdbc27dbtrgkipe


2011 2011 6th International ICST Conference on Communications and Networking in China (CHINACOM)  
wireless network selection algorithm based on non-720 cooperative game theory A New Improved MAC Scheme: RM-MAC 822 wenbin zhang, xiaozong yang, shaochuan wu The UESTC Reconfigurable Cognitive Radio Testbed  ...  939 zhaojun he, tian liu, youxi tang, qiang xu, wensheng pan A Novel Design of Cognitive Wireless Networks-Architecture and Testbed 944 All-optical VPN in optical OFDMA-based PON for integration of optical  ...  A New In-domain Interconnected Architecture Based On Tree-based Topology 730 Cheng Yang, Zhenhua Liu, Du Xu Topology Design of Industrial Ethernet Networks Using a Multi-objective 735 Genetic Algorithm  ... 
doi:10.1109/chinacom.2011.6158106 fatcat:wwiuivqaejhcnpyglnodfcnqem

TSN Switch Queue Length Prediction Based on an Improved LSTM Network

Xin Wang, Zhijun Shang, Changqing Xia, Shijie Cui, Shuai Shao, Deepak Kumar Jain
2021 Wireless Communications and Mobile Computing  
Finally, the results of the simulation demonstrate that our proposed TSN switch queue length prediction model based on the improved LSTM network algorithm doubles the prediction accuracy compared to the  ...  The input-output structure of the network is changed based on the extracted features to improve the prediction accuracy, thus predicting the network congestion caused by bursty traffic.  ...  Acknowledgments This work is supported by the National Key R&D Program of China (2018YFB1700103) and the National Natural Science Foundation of China (61903356).  ... 
doi:10.1155/2021/5130888 fatcat:7zeeip2tsvcxjh5addseme6kja

Optimization of Deep Neural Networks Using SoCs with OpenCL

Rafael Gadea-Gironés, Ricardo Colom-Palero, Vicente Herrero-Bosch
2018 Sensors  
In the optimization of deep neural networks (DNNs) via evolutionary algorithms (EAs) and the implementation of the training necessary for the creation of the objective function, there is often a trade-off  ...  This paper first presents a study that demonstrates the need for a heterogeneous (CPU-GPU-FPGA) platform to accelerate the optimization of artificial neural networks (ANNs) using genetic algorithms.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s18051384 pmid:29710875 pmcid:PMC5982427 fatcat:frf265t2ejeubgjhdlyg7xcpji

A Method of Optimizing Network Topology Structure Combining Viterbi Algorithm and Bayesian Algorithm

Xiaoxiao Shi, Rahim Khan
2021 Wireless Communications and Mobile Computing  
Dual planning of improved Viterbi algorithm is used to realize the main and standby path planning, and then, Bayesian recommendation algorithm based on the average value is used to optimize the network  ...  In this paper, a method for optimizing the topological structure of the bottom layer of the communication network is proposed that has outage performance close to optimal routing scheme.  ...  Acknowledgments This work is funded by the National Natural Science Foundation of China under Grant No. 61772180.  ... 
doi:10.1155/2021/5513349 fatcat:zkaz6gwzvfdbtblcyzbmjh5b2e

Research on Early Warning Model of College Students' Psychological Crisis Based on Genetic BP Neural Network

Jia Wang, Zijie Zhang, Haiji Luo, Yinghao Liu, Wei Chen, Gang Wei
2019 American Journal of Applied Psychology  
With experimental simulation of 250 sets of real data, the early warning model based on the genetic BP Neural network for its initial weight and threshold with MATLAB was improved.  ...  Jia Wang et al.: Research on Early Warning Model of College Students' Psychological Crisis Based on Genetic BP Neural Network assessment [7].  ...  My paper is supported by the Scientific and Technological Research Program of Chongqing Municipal Education Commission, China (General program). Grant No. 17SKG026.  ... 
doi:10.11648/j.ajap.20190806.12 fatcat:yqtmrwbfzfdornncf7t2ai6a2m

Artificial intelligence (AI) methods in optical networks: A comprehensive survey

Javier Mata, Ignacio de Miguel, Ramón J. Durán, Noemí Merayo, Sandeep Kumar Singh, Admela Jukan, Mohit Chamania
2018 Optical Switching and Networkning Journal  
This paper presents a comprehensive review of the application of AI techniques for improving performance of optical communication systems and networks.  ...  The use of AI-based techniques is first studied in applications related to optical transmission, ranging from the characterization and operation of network components to performance monitoring, mitigation  ...  Acknowledgment This work has been partially supported by the Spanish Ministry of Economy and Competitiveness (TEC2014-53071-C3-2-P, TEC2015-71932-REDT).  ... 
doi:10.1016/j.osn.2017.12.006 fatcat:i443tt6fv5g2jmvfe7kn57unbq

A network security situation prediction model based on wavelet neural network with optimized parameters

Haibo Zhang, Qing Huang, Fangwei Li, Jiang Zhu
2016 Digital Communications and Networks  
In order to improve the prediction accuracy of the network security situation, we build a network security situation prediction model based on Wavelet Neural Network (WNN) with optimized parameters by  ...  the Improved Niche Genetic Algorithm (INGA).  ...  Conclusion In this paper, we put forward a network security situation prediction model, which is based on WNN with the parameters optimized by the improved niche genetic algorithm.  ... 
doi:10.1016/j.dcan.2016.06.003 fatcat:y5vchmqt5baophpvjfoohcukaa

An Approach for Breast Cancer Diagnosis Classification Using Neural Network

Htet Thazin Tike Thein, Khin Mo Mo Tun
2015 Advanced Computing An International Journal  
The proposed system implements the island-based training method to be better accuracy and less training time by using and analysing between two different migration topologies.  ...  To overcome this problem, differential evolution algorithm (DE) has been used to determine optimal value or near optimal value for ANN parameters.  ...  To achieve this, we propose a solution based on the concept of neural networks [2] [3] [4] .  ... 
doi:10.5121/acij.2015.6101 fatcat:gu67dkh5d5dhhmnuer46czimm4

Scanning the Issue

Azim Eskandarian
2020 IEEE transactions on intelligent transportation systems (Print)  
The BN topology is structured based on the physical relationships among data types.  ...  Through simulated experiments, over six different communication topologies, the improvements of the proposed control law are illustrated.  ...  Tang In this article, the train-centric communication-based train control (CBTC) systems through train-to-train (T2T) wireless communication is introduced based on the modification of LTE vehicle-to-everything  ... 
doi:10.1109/tits.2020.3021574 fatcat:cpxn24tjyvbcxf3fodglepuwsi

Dynamic Routings in Satellite Networks: An Overview

Xiaoli Cao, Yitao Li, Xingzhong Xiong, Jun Wang
2022 Sensors  
Afterward, dynamic routing problems in satellite networks are analyzed in detail based on the time-varying network topology.  ...  The Satellite network is an important part of the global network.  ...  Therefore, the work in [55] proposed an S-IoT adaptive routing algorithm based on improved dual-Q learning.  ... 
doi:10.3390/s22124552 pmid:35746331 pmcid:PMC9231381 fatcat:lmac3ns7dnfgbj3232nlyxik7u
« Previous Showing results 1 — 15 out of 11,430 results