在Rust 中实现 ENT2 神经进化遗传算法_rust_代码_下载

上传者: 38334677 | 上传时间: 2022-06-12 14:05:22 | 文件大小: 22.55MB | 文件类型: ZIP
该库使用进化算法 ( EA ) 自动进化群体中每个个体的人工神经网络的拓扑结构。 进化算法属于进化计算研究领域,涉及受生物进化过程和机制启发的计算方法。达尔文提出了通过自然选择(通过修改下降)的进化过程,以说明生命的多样性及其对环境的适应性(适应性适应)。进化机制描述了进化是如何通过遗传物质(蛋白质)的修饰和繁殖实际发生的。进化算法关注的是研究类似于进化过程和机制的简化版本的计算系统,以实现这些过程和机制的效果,即自适应系统的发展。属于进化计算领域的其他学科领域是寻求利用种群遗传学、种群生态学、协同进化生物学和发育生物学相关领域的属性的算法。--聪明的算法.com 人工神经网络的特征在于它们的结构(拓扑)和它们的参数(包括连接的权重)。因此,当为给定问题开发 ANN 时,需要考虑两个方面: 网络的结构(或拓扑)应该是什么? 给定神经网络的结构,其参数的最佳值是多少? EANT2,Evolutionary Acquisition of Neural Topologies,是一种进化强化学习系统,适合通过交互来学习和适应环境。它结合了神经网络、强化学习和进化方法的原理。

文件下载

资源详情

[{"title":"( 37 个子文件 22.55MB ) 在Rust 中实现 ENT2 神经进化遗传算法_rust_代码_下载","children":[{"title":"fluffy-penguin-master","children":[{"title":".travis.yml <span style='color:#111;'> 127B </span>","children":null,"spread":false},{"title":".github","children":[{"title":"workflows","children":[{"title":"rust.yml <span style='color:#111;'> 586B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"tests","children":[{"title":"individual.rs <span style='color:#111;'> 713B </span>","children":null,"spread":false},{"title":"population.rs <span style='color:#111;'> 2.83KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 33.71KB </span>","children":null,"spread":false},{"title":".rustfmt.toml <span style='color:#111;'> 28B </span>","children":null,"spread":false},{"title":"src","children":[{"title":"utils.rs <span style='color:#111;'> 488B </span>","children":null,"spread":false},{"title":"error.rs <span style='color:#111;'> 2.16KB </span>","children":null,"spread":false},{"title":"cge","children":[{"title":"node.rs <span style='color:#111;'> 5.51KB </span>","children":null,"spread":false},{"title":"mod.rs <span style='color:#111;'> 802B </span>","children":null,"spread":false},{"title":"network.rs <span style='color:#111;'> 57.32KB </span>","children":null,"spread":false}],"spread":true},{"title":"genetic_algorithm","children":[{"title":"mod.rs <span style='color:#111;'> 152B </span>","children":null,"spread":false},{"title":"individual.rs <span style='color:#111;'> 22.06KB </span>","children":null,"spread":false},{"title":"mutation.rs <span style='color:#111;'> 1.53KB </span>","children":null,"spread":false},{"title":"population.rs <span style='color:#111;'> 17.44KB </span>","children":null,"spread":false}],"spread":true},{"title":"activation.rs <span style='color:#111;'> 5.69KB </span>","children":null,"spread":false},{"title":"lib.rs <span style='color:#111;'> 7.11KB </span>","children":null,"spread":false}],"spread":true},{"title":"Cargo.toml <span style='color:#111;'> 403B </span>","children":null,"spread":false},{"title":"doc","children":[{"title":"Analysis of an Evolutionary Reinforcement Learning Method in a Multiagent Domain.pdf <span style='color:#111;'> 1.29MB </span>","children":null,"spread":false},{"title":"Efficient Evolution of Neural Networks Through Complexification (2004) stanley.phd04.pdf <span style='color:#111;'> 14.65MB </span>","children":null,"spread":false},{"title":"CMA-ES_and_advanced_adaptation_mechanisms.pdf <span style='color:#111;'> 5.72MB </span>","children":null,"spread":false},{"title":"EANT2 - SiebelSommerKassahun-EANT2-CIMI2008.pdf <span style='color:#111;'> 764.25KB </span>","children":null,"spread":false},{"title":"A General Framework for Encoding and Evolving Neural Networks.pdf <span style='color:#111;'> 442.14KB </span>","children":null,"spread":false},{"title":"A Common Genetic Encoding for Both Direct and Indirect.pdf <span style='color:#111;'> 246.85KB </span>","children":null,"spread":false},{"title":"EANT2 with prune - 10.1.1.158.8673_2009.pdf <span style='color:#111;'> 341.92KB </span>","children":null,"spread":false},{"title":"MO-CMA-ES_voss2010improved.pdf <span style='color:#111;'> 271.77KB </span>","children":null,"spread":false},{"title":"Specimen_example.svg <span style='color:#111;'> 182.30KB </span>","children":null,"spread":false},{"title":"CMA-ES.pdf <span style='color:#111;'> 1.10MB </span>","children":null,"spread":false},{"title":"MO-CMA-ES Covariance Matrix Adaptation for Multi-objective Optimization.pdf <span style='color:#111;'> 653.10KB </span>","children":null,"spread":false},{"title":"Towards a Unified Approach to Learning and Adaptation.pdf <span style='color:#111;'> 2.79MB </span>","children":null,"spread":false},{"title":"Introduction_to_Evolutionary_Computing.pdf <span style='color:#111;'> 3.96MB </span>","children":null,"spread":false},{"title":"Specimen_example_at_initial_generation.svg <span style='color:#111;'> 24.78KB </span>","children":null,"spread":false}],"spread":false},{"title":"examples","children":[{"title":"mnist.rs <span style='color:#111;'> 8.85KB </span>","children":null,"spread":false},{"title":"basic.rs <span style='color:#111;'> 7.68KB </span>","children":null,"spread":false},{"title":"playground.rs <span style='color:#111;'> 17.37KB </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 459B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.58KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明