发布求助
文献互助 智能选刊 最新文献

Proceedings of the Companion Conference on Genetic and Evolutionary Computation最新文献

筛选
英文 中文
Evolution of Neural Networks 神经网络的进化
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3595036
R. Miikkulainen
{"title":"Evolution of Neural Networks","authors":"R. Miikkulainen","doi":"10.1145/3583133.3595036","DOIUrl":"https://doi.org/10.1145/3583133.3595036","url":null,"abstract":"I . Original role (since 1990s): RL Tasks & especially POMDP I Both the structure and the weights evolved (no training) I Power from recurrency; behavior I . A new role (since 2016): Optimization of Deep Learning Nets I Architecture, hyperparameters, functions evolved; weights trained I Power from complexity I . A possible future role: Emergence of intelligence I Body/brain co-evolution; Competitive co-evolution I Evolution of memory, language, learning 3/62 I. Reinforcement Learning / POMDP Tasks","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129673599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Hybrid Rocket Engine Design Using Pairwise Ranking Surrogate-assisted Differential Evolution 基于两两排序代理辅助差分进化的混合火箭发动机设计
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3596379
Hitomi Kano, Tomohiro Harada, Y. Miura, Masahiro Kanazaki
{"title":"Hybrid Rocket Engine Design Using Pairwise Ranking Surrogate-assisted Differential Evolution","authors":"Hitomi Kano, Tomohiro Harada, Y. Miura, Masahiro Kanazaki","doi":"10.1145/3583133.3596379","DOIUrl":"https://doi.org/10.1145/3583133.3596379","url":null,"abstract":"Real-world optimization problems often require time-consuming fitness evaluations because of simulations or complex numerical calculations. A hybrid rocket engine (HRE) design problem is a time-consuming real-world application. HRE is a rocket engine that stores either the oxidizer or fuel in solid form and the other in liquid form. A surrogate model can reduce the number of expensive objective/constraint function calculations for such expensive optimization problems by searching for promising solutions. This study applies a new surrogate-assisted constraint-handling evolutionary algorithm, CHDE+ELDR, to solve the HRE design problem with fewer evaluations. CHDE+ELDR combines CHDE, a constraint-handling differential evolution, and ELDR, a pairwise ranking surrogate model. We conduct an experiment on the HRE design problem with limited evaluations and compare CHDE+ELDR with CHDE without a surrogate model. The experimental results show that CHDE+ELDR can consistently obtain high-quality HRE designs with fewer evaluations than simple CHDE.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130874437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Lexicase Selection Lexicase选择
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3595035
William George La Cava, Thomas Helmuth
{"title":"Lexicase Selection","authors":"William George La Cava, Thomas Helmuth","doi":"10.1145/3583133.3595035","DOIUrl":"https://doi.org/10.1145/3583133.3595035","url":null,"abstract":"","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128901637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimizing Telemetry Signal Influence for Power Consumption Prediction 优化遥测信号对功耗预测的影响
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3596431
Pawel Benecki, Daniel Kostrzewa, P. Grzesik, B. Shubyn, Dariusz Mrozek
{"title":"Optimizing Telemetry Signal Influence for Power Consumption Prediction","authors":"Pawel Benecki, Daniel Kostrzewa, P. Grzesik, B. Shubyn, Dariusz Mrozek","doi":"10.1145/3583133.3596431","DOIUrl":"https://doi.org/10.1145/3583133.3596431","url":null,"abstract":"Automated Guided Vehicles (AGVs) are common elements of contemporary industry. Their continuous operation, and thus detection of anomalies in their operational cycles, is critical for uninterrupted production flow. Prediction of signals, such as momentary power consumption (MPC), is used in most anomaly detection methods. Feature engineering - selection or weighting - can significantly improve prediction quality. In this work, we use a genetic algorithm (GA) to optimize weights for features from AGV telemetry. A 2-layer Long Short-Term Memory (LSTM) network was used to predict MPC. Our primary goal was identifying the most effective weighting strategy for enhancing predictive accuracy. We examined different schemes of population initialization. The performance of each was compared to baseline models. Results show a significant improvement in prediction quality compared to the baseline. Our application of GA optimization in feature engineering contributes to the growing body of knowledge on developing more reliable AGV systems, which can lead to reduced operational costs and enhanced sustainability in various industrial settings.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115998556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Variable neighborhood search for solving the k-domination problem 求解k-支配问题的可变邻域搜索
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3590607
M. Predojević, Aleksandar Kartelj, M. Djukanović
{"title":"Variable neighborhood search for solving the k-domination problem","authors":"M. Predojević, Aleksandar Kartelj, M. Djukanović","doi":"10.1145/3583133.3590607","DOIUrl":"https://doi.org/10.1145/3583133.3590607","url":null,"abstract":"In this paper we are concerned with solving a generalized version of the well-known minimum dominating set problem, the so-called k-domination problem, k ∈ ℕ. This problem is about finding a minimal cardinality subset D of vertices of a graph G = (V, E) such that every υ ∈ V belongs to D or has at least k neighbors from D. The k-domination problem has applications in distributed systems, biological networks etc. We propose a variable neighborhood search (VNS) metaheuristic for solving the k-domination problem. The Vns is equipped with an efficient fitness function that allows it to consider both feasible and infeasible solutions, while appropriately penalizing infeasible solutions. The control parameters of the Vns are tuned using a grid search approach. The method is compared to the best known heuristic approaches from the literature: the beam search and several greedy approaches. Experimental evaluations are performed on a real-world benchmark set whose instances represent the road networks of different cities. The Vns provided new state-of-the-art results for all considered problem instances with k ∈ {1, 2, 4}.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"255 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116014038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture 一种基于ResNet体系结构的辅助评价度量神经结构搜索方法
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3590618
Shang Wang, Huanrong Tang, Jian-quan Ouyang
{"title":"A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture","authors":"Shang Wang, Huanrong Tang, Jian-quan Ouyang","doi":"10.1145/3583133.3590618","DOIUrl":"https://doi.org/10.1145/3583133.3590618","url":null,"abstract":"This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116475917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An analysis of choice functions for Fuzzy ART using grammatical evolution 基于语法演化的模糊ART选择函数分析
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3590554
Mia Gerber, N. Pillay
{"title":"An analysis of choice functions for Fuzzy ART using grammatical evolution","authors":"Mia Gerber, N. Pillay","doi":"10.1145/3583133.3590554","DOIUrl":"https://doi.org/10.1145/3583133.3590554","url":null,"abstract":"The Fuzzy Adaptive Resonance Theory (ART) algorithm is effective for unsupervised clustering. The Fuzzy ART choice function is an integral part of the Fuzzy ART algorithm. One of the challenges is that different choice functions are effective for different datasets. This work evolves the choice function using GE. The study compares the evolved choice functions to manually created choice functions. This study compares two different grammars for the GE, a basic grammar that includes only functions from the Fuzzy ART algorithm and an extended grammar that includes additional functions. This work also compares different fitness functions for GE. Analysis is done using ten UCI benchmark datasets and three real-world sentiment analysis datasets, it is found that the evolved functions using the extended grammar perform better than the manually created functions. The best fitness function to use for the GE is dataset dependent.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126680380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Theory and Practice of Population Diversity in Evolutionary Computation 种群多样性在进化计算中的理论与实践
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3595053
Dirk Sudholt, Giovanni Squillero
{"title":"Theory and Practice of Population Diversity in Evolutionary Computation","authors":"Dirk Sudholt, Giovanni Squillero","doi":"10.1145/3583133.3595053","DOIUrl":"https://doi.org/10.1145/3583133.3595053","url":null,"abstract":"","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125802947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Constraint-Handling Techniques used with Evolutionary Algorithms 进化算法中使用的约束处理技术
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3595032
C. C. Coello Coello
{"title":"Constraint-Handling Techniques used with Evolutionary Algorithms","authors":"C. C. Coello Coello","doi":"10.1145/3583133.3595032","DOIUrl":"https://doi.org/10.1145/3583133.3595032","url":null,"abstract":"","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Transfer Learning for Embodied Neuroevolution 具身神经进化的迁移学习
Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI: 10.1145/3583133.3596400
Divya D. Kulkarni, S. B. Nair
{"title":"Transfer Learning for Embodied Neuroevolution","authors":"Divya D. Kulkarni, S. B. Nair","doi":"10.1145/3583133.3596400","DOIUrl":"https://doi.org/10.1145/3583133.3596400","url":null,"abstract":"Transfer Learning (TL) has been widely used in machine learning where the neuronal layers in a learned source Artificial Neural Network (ANN) are transferred to a target ANN so as to speed up the latter's learning. TL most often requires that the source and target domains are similar. However, its use in dissimilar domains as also in ANNs that use neuroevolution strategies has hardly been investigated. In this paper, we present a mechanism, suited for neuroevolution, that can identify specific neurons that need to be transferred. These Hot neurons from the source ANN, when transferred to the target ANN, helps in hastening the learning at the target. Simulations conducted using robots, clearly indicate that the mechanism is well suited for both similar and dissimilar tasks or environments.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127743778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信