424,529 Hits in 5.2 sec

Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks [chapter]

P. A. Castillo, M. G. Arenas, J. J. Merelo, G. Romero, F. Rateb, A. Prieto
2004 Lecture Notes in Computer Science  
approach to optimize the architecture and initial weights of multilayer perceptrons; a method that searches for the parameters of the training algorithm, and an approach for cooperative co-evolutionary  ...  optimization of multilayer perceptrons.  ...  The authors are grateful to anonymous referees for their constructive comments and advice about the first revision of our paper.  ... 
doi:10.1007/978-3-540-24650-3_22 fatcat:jlbctado65ho3fxwvic3zlam2u

Evolutionary Architecture Search for Graph Neural Networks [article]

Min Shi, David A.Wilson, Xingquan Zhu, Yu Huang, Yuan Zhuang, Jianxun Liu, Yufei Tang
2020 arXiv   pre-print
Instead of optimizing only the model structures with fixed parameter settings as existing work, an alternating evolution process is performed between GNN structures and learning parameters to dynamically  ...  In addition, the slight variation of hyper parameters such as learning rate and dropout rate could dramatically hurt the learning capacity of GNN.  ...  Then, the population (P 0 ) of GNN parameters w.r.t S 0 is initialized and evolved to identify the optimal parameter setting (e.g., learning rate and dropout rate).  ... 
arXiv:2009.10199v1 fatcat:k2h23byz2jfebbiw3mzckveblm

Parameter Optimization with Restarting Genetic Algorithm for the Forest Type Classification

Keerachart Suksut, Nuntawut Kaoungku, Nittaya Kerdprasop, Kittisak Kerdprasop
2017 International Journal of Machine Learning and Computing  
The genetic algorithm is the search algorithm for optimal answer with adaptive heuristic search based on the evolutionary characteristic of nature.  ...  Support vector machine is a parametric approach such that proper setting of parameter value can directly influence the classifying performance of the machine.  ...  The authors are with the School of Computer Engineering, Suranaree University of Technology (SUT), 111 University Avenue, Muang, Nakhon Ratchasima 30000, Thailand (corresponding author: K.  ... 
doi:10.18178/ijmlc.2017.7.6.649 fatcat:edangrq6d5guvdfypjadebcyja

A Multi-Strategy Adaptive Comprehensive Learning PSO Algorithm and Its Application

Ye'e Zhang, Xiaoxia Song
2022 Entropy  
In this paper, a multi-strategy adaptive comprehensive learning particle swarm optimization algorithm is proposed by introducing the comprehensive learning, multi-population parallel, and parameter adaptation  ...  Finally, some benchmark functions and the parameter optimization of photovoltaics are selected. The proposed algorithm obtains the best performance on 6 out of 10 functions.  ...  Acknowledgments: Thank you very much for contribution of Deng. Institutional Review  ... 
doi:10.3390/e24070890 pmid:35885113 pmcid:PMC9317180 fatcat:tn4mgxnljvbi3fk5gk5k3ifmwe

PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments [article]

Qihao Liu, Yujia Wang, Xiaofeng Liu
2021 arXiv   pre-print
The chief agent evaluates the policies learned by exploring agents and shares the optimal policy with all sub-populations.  ...  The exploring agents learn their policies in collaboration with the guidance of the optimal policy and, simultaneously, upload their policies to the chief agent.  ...  Population-Based Training (PBT) PBT is another kind of parallel algorithm used for finding optimal parameters of a network model [12] .  ... 
arXiv:1811.10264v4 fatcat:acgmzw4iubbnjnbfcngusulz5y

Hyperparameter Optimization for Deep Learning-based Automatic Melanoma Diagnosis System

Takashi Nagaoka
2020 Advanced Biomedical Engineering  
Deep learning is widely used in the development of automatic diagnosis systems for melanoma. However, there are some parameters called hyperparameters which should be set arbitrarily.  ...  By using a genetic algorithm, these hyperparameters were optimized to obtain higher validation accuracy than other methods such as brute force or Bayesian optimization.  ...  Several approaches have been devised for optimization of the various parameters of deep learning. Lorenzo et al. [6] used Particle Swarm Optimization, and Young et al.  ... 
doi:10.14326/abe.9.225 fatcat:2xylaqkxgbdhvdnnmzmp6b3t5q

Optimization Forecasting using Back-Propagation Algorithm

Budi Raharjo, Nurul Farida, Purwo Subekti, Rima Herlina S Siburian, Putu Doddy Heka Ardana, Robbi Rahim
2021 Istrazivanja i projektovanja za privredu  
Parameter optimization is changing the learning rate (lr) of the backpropagation prediction model.  ...  The purpose of this study was to evaluate the back-propagation model by optimizing the parameters for the prediction of broiler chicken populations by provinces in Indonesia.  ...  This paper proposes an optimization of the activation function and the sigmoid function with three parameters. this is done because this parameter affects the speed of learning. the results of the study  ... 
doi:10.5937/jaes0-30175 fatcat:2z6kdk2yibdrzemn6fhx3bjp5q

Network Traffic Classification using Genetic Algorithms based on Support Vector Machine

Jie Cao, Zhiyi Fang
2016 International Journal of Security and Its Applications  
The method extracts a certain number population from random solutions, and ultimately produces SVM optimal parameters according to the specific rules of operation.  ...  How to determine the optimal parameters of SVM is a problem to be solved.  ...  However, this method is very time-consuming to find the optimal parameters in a wider range. We proposed a method for deriving the optimal parameters of SVM based on GA [14] .  ... 
doi:10.14257/ijsia.2016.10.2.21 fatcat:mnxbeizoybertgysas5qylszy4

Optimal selection of parameters in CNC end milling of Al 7075 T6 alloy by TBLO

Fauzia Siddiqui, Paramjit Thakur
2019 International Journal of Engineering Sciences  
The regression model was used by Teaching Learning Based Optimization (TLBO) algorithm and optimum process parameters were obtained.  ...  The optimal process parameters obtained by TLBO gave 60% reduction in roughness as compared to that given by initial setting of parameters used for machining of this material.  ...  teaching learning based optimization in finding the optimal process parameter in CNC end milling of AL 7075 t6 alloy.  ... 
doi:10.36224/ijes.110405 fatcat:ztbtr4vfpfbmdgq4imqd3dtdle

Traffic Flow Prediction Using SPGAPSO-CKRVM Model

Hao Lin, Leixiao Li, Hui Wang, Yongsheng Wang, Zhiqiang Ma
2020 Revue d'intelligence artificielle : Revue des Sciences et Technologies de l'Information  
Second, a parameter optimization algorithm is proposed to optimize the parameters of combined kernel functions by Genetic Algorithm and Particle Swarm Optimization.  ...  Traffic flow prediction is popular research of ITS. Traffic flow prediction models based on machine learning have recently been widely applied.  ...  Time-consuming analysis of parameter optimization algorithm GA and PSO in parameter optimization algorithm designed in this paper can be divided into three parts-population initiation, population update  ... 
doi:10.18280/ria.340303 fatcat:ggcbvdqjjfafbii4i2q7p4brqq

Momentum Backpropagation Optimization for Cancer Detection Based on DNA Microarray Data

Untari Novia Wisesty, Febryanti Sthevanie, Rita Rismala
2021 International Journal of Artificial Intelligence Research  
Therefore, in this research an optimization of the Momentum Backpropagation algorithm is done by adding an adaptive learning rate scheme.  ...  Early detection of cancer can increase the success of treatment in patients with cancer. In the latest research, cancer can be detected through DNA Microarrays.  ...  Hyper parameters observed were population size, crossover probability, mutation probability, number of hidden neurons, and Backpropagation algorithm with an adaptive learning rate parameter (learning rate  ... 
doi:10.29099/ijair.v4i2.188 fatcat:simadhkdurcphnqmexzohvivye

Fuzzy Multi-SVR Learning Model for Reliability-Based Design Optimization of Turbine Blades

Chun-Yi Zhang, Ze Wang, Cheng-Wei Fei, Zhe-Shan Yuan, Jing-Shan Wei, Wen-Zhong Tang
2019 Materials  
The model of fuzzy multi-SVR learning method was established by adopting artificial bee colony algorithm to optimize the parameters of SVR models and considering the fuzziness of constraints based on fuzzy  ...  The effectiveness of a model is the key factor of influencing the reliability-based design optimization (RBDO) of multi-failure turbine blades in the power system.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ma12152341 pmid:31344790 pmcid:PMC6696244 fatcat:oaxfrrrtrbh4hno7rylbcwkjmu

Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks [article]

Xiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny
2018 arXiv   pre-print
fitness of the population.  ...  In addition, individuals in the population optimized with various SGD-based optimizers using distinct hyper-parameters in the SGD step are considered as competing species in a coevolution setting such  ...  Each individual represents a set of model parameters to be optimized by an optimizer (e.g. conventional SGD, Nesterov accelerated SGD or ADAM) with a distinct set of hyper-parameters (e.g. learning rate  ... 
arXiv:1810.06773v1 fatcat:4vyjnr3acfd3fosu2rije64ubu

Parameter Adaptation within Co-adaptive Learning Classifier Systems [chapter]

Chung-Yuan Huang, Chuen-Tsai Sun
2004 Lecture Notes in Computer Science  
The authors propose a co-adaptive approach to controlling parameters for coevolution-based learning classifier systems.  ...  The system combines the advantages of both adaptive and self-adaptive parameter-control approaches.  ...  learning performance and population size state, and still rebuild an optimal solution.  ... 
doi:10.1007/978-3-540-24855-2_92 fatcat:xxzbwm3hvrcsjcog7ikgu2sheu

Fast Weak Learner Based on Genetic Algorithm [article]

Boris Yangel
2009 arXiv   pre-print
Genetic algorithm is used instead of exhaustive search to learn parameters of such classifier.  ...  Proposed approach also takes cases when effective algorithm for learning some of the classifier parameters exists into account.  ...  So, set of parameters x1, . . . , x n−l represents solution to our optimization problem and form up a member of genetic algorithm population.  ... 
arXiv:0906.0872v1 fatcat:yqw2xw72lvbi7ancsmoy5c7weq
« Previous Showing results 1 — 15 out of 424,529 results