检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

10 篇 会议

馆藏范围

10 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10 篇 工学
- 9 篇 计算机科学与技术...
- 4 篇 软件工程
- 2 篇 控制科学与工程
- 1 篇 机械工程
- 1 篇 仪器科学与技术
- 1 篇 电气工程
2 篇 理学
- 2 篇 数学
- 1 篇 生物学
1 篇 农学
- 1 篇 作物学
1 篇 管理学
- 1 篇 管理科学与工程(可...

主题

10 篇 compositional pa...
4 篇 neat
3 篇 cppns
2 篇 voxcad
2 篇 indirect encodin...
2 篇 genotype
2 篇 phenotype
2 篇 hyperneat
2 篇 large-scale arti...
1 篇 neuroevolution o...
1 篇 decision-making ...
1 篇 generative adver...
1 篇 iec
1 篇 neuroevolution
1 篇 fourlegs walking
1 篇 generative and d...
1 篇 generative encod...
1 篇 parametric
1 篇 four-legged walk...
1 篇 checkers

机构

2 篇 univ cent florid...
1 篇 pn engineering c...
1 篇 hangzhou dianzi ...
1 篇 it univ copenhag...
1 篇 zhejiang tsinghu...
1 篇 univ cent florid...
1 篇 dept. of eecs co...
1 篇 univ cent florid...
1 篇 rocket force uni...
1 篇 bonn rhein sieg ...
1 篇 school of automa...
1 篇 modl ai copenhag...
1 篇 southwestern uni...
1 篇 google deepmind ...

作者

4 篇 stanley kenneth ...
2 篇 gauci jason
1 篇 pfau david
1 篇 schrum jacob
1 篇 wu qiuxuan
1 篇 hagg alexander
1 篇 zhang xuecheng
1 篇 d'ambrosio david...
1 篇 jaderberg max
1 篇 lanctot marc
1 篇 scarton ludovico
1 篇 zhang botao
1 篇 fernando chrisan...
1 篇 gu yueqin
1 篇 luo yanbin
1 篇 li yancheng
1 篇 wierstra daan
1 篇 hoover amy k.
1 篇 risi sebastian
1 篇 yueqin gu

语言

10 篇 英文

检索条件"主题词=Compositional Pattern Producing Networks"

共 10 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

CPPN2GAN: Combining compositional pattern producing networks and GANs for Large-scale pattern Generation

CPPN2GAN: Combining Compositional Pattern Producing Networks...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Schrum, Jacob Volz, Vanessa Risi, Sebastian Southwestern Univ Georgetown TX 78626 USA Modl Ai Copenhagen Denmark IT Univ Copenhagen Modl Ai Copenhagen Denmark

ISBN: (纸本)9781450371285

Generative Adversarial networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels. Game levels often consist of several segments, sometimes repeated directly or with variation, organized into an engaging pattern. Such patterns can be produced with compositional pattern producing networks (CPPNs). Specifically, a CPPN can define latent vector GAN inputs as a function of geometry, which provides a way to organize level segments output by a GAN into a complete level. This new CPPN2GAN approach is validated in both Super Mario Bros. and The Legend of Zelda. Specifically, divergent search via MAP-Elites demonstrates that CPPN2GAN can better cover the space of possible levels. The layouts of the resulting levels are also more cohesive and aesthetically consistent.

关键词： compositional pattern producing networks Generative Adversarial networks Indirect Encoding Neuroevolution

来源：评论

学校读者我要写书评

暂无评论

Convolution by Evolution Differentiable pattern producing networks 16

Convolution by Evolution Differentiable Pattern Producing Ne...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Fernando, Chrisantha Banarse, Dylan Reynolds, Malcolm Besse, Frederic Pfau, David Jaderberg, Max Lanctot, Marc Wierstra, Daan Google DeepMind London England

ISBN: (纸本)9781450342063

In this work we introduce a differentiable version of the compositional pattern producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines evolution and learning, produces DPPNs to reconstruct an image. Our main result is that DPPNs can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters, while achieving a reconstruction accuracy comparable to a fully connected network with more than two orders of magnitude more parameters. The regularization ability of the DPPN allows it to rediscover (approximate) convolutional network architectures embedded within a fully connected architecture. Such convolutional architectures are the current state of the art for many computer vision applications, so it is satisfying that DPPNs are capable of discovering this structure rather than having to build it in by design. DPPNs exhibit better generalization when tested on the Omniglot dataset after being trained on MNIST, than directly encoded fully connected autoencoders. DPPNs are therefore a new framework for integrating learning and evolution.

关键词： CPPNs compositional pattern producing networks denoising autoencoder MNIST

来源：评论

学校读者我要写书评

暂无评论

Evolving Neural networks for Geometric Game-Tree Pruning 11

Evolving Neural Networks for Geometric Game-Tree Pruning

引用

13th Annual Genetic and Evolutionary Computation Conference (GECCO)

作者： Gauci, Jason Stanley, Kenneth O. Univ Cent Florida Dept EECS Orlando FL 32836 USA

ISBN: (纸本)9781450305570

Game-tree search is the engine behind many computer game opponents. Traditional game-tree search algorithms decide which move to make based on simulating actions, evaluating future board states, and then applying the evaluations to estimate optimal play by all players. Yet the limiting factor of such algorithms is that the search space increases exponentially with the number of actions taken (i.e. the depth of the search). More recent research in game-tree search has revealed that even more important than evaluating future board states is effective pruning of the search space. Accordingly, this paper discusses Geometric Game-Tree Pruning (GGTP), a novel evolutionary method that learns to prune game trees based on geometric properties of the game board. The experiment compares Cake, a minimax-based game-tree search algorithm, with HyperNEAT-Cake, the original Cake algorithm combined with an indirectly encoded, evolved GGTP algorithm. The results show that HyperNEAT-Cake wins significantly more games than regular Cake playing against itself.

关键词： compositional pattern producing networks NEAT Hyper-NEAT Checkers Decision-Making Domains Game-Trees

来源：评论

学校读者我要写书评

暂无评论

Scaffolding for interactively evolving novel drum tracks for existing songs

引用

EvoWorkshops 2008

作者： Hoover, Amy K. Rosario, Michael P. Stanley, Kenneth O. Univ Cent Florida Sch Elect Engn & Comp Sci Evolut Complex Res Grp Orlando FL 32836 USA

ISBN: (纸本)9783540787600

A major challenge in computer-generated music is to produce music that sounds natural. This paper introduces NEAT Drummer, which takes steps toward natural creativity. NEAT Drummer evolves a kind of artificial neural network called a compositional pattern producing Network (CPPN) with the NeuroEvolution of Augmenting Topologies (NEAT) method to produce drum patterns. An important motivation for this work is that instrument tracks can be generated as a function of other song parts, which, if written by humans, thereby provide a scaffold for the remaining auto-generated parts. Thus, NEAT Drummer is initialized with inputs from an existing MIDI song and through interactive evolution allows the user to evolve increasingly appealing rhythms for that song. This paper explains how NEAT Drummer processes MIDI inputs and outputs drum patterns. The net effect is that a compelling drum track can be automatically generated and evolved for any song.

关键词： compositional pattern producing networks CPPNs computer-generated music interactive evolutionary computation IEC NeuroEvolution of Augmenting Topologies NEAT

来源：评论

学校读者我要写书评

暂无评论

A Novel Generative Encoding for Exploiting Neural Network Sensor and Output Geometry 07

A Novel Generative Encoding for Exploiting Neural Network Se...

引用

Annual Conference of Genetic and Evolutionary Computation Conference

作者： D'Ambrosio, David B. Stanley, Kenneth O. Univ Cent Florida Sch EECS Evolutionary Complex Res Grp Orlando FL 32836 USA

ISBN: (纸本)9781595936974

A significant problem for evolving artificial neural networks is that the physical arrangement of sensors and effectors is invisible to the evolutionary algorithm. For example, in this paper, directional sensors and effectors are placed around the circumference of a robot in analogous arrangements. This configuration ensures that there is a useful geometric correspondence between sensors and effectors. However, if sensors are mapped to a single input layer and the effectors to a single output layer (as is typical), evolution has no means to exploit this fortuitous arrangement. To address this problem, this paper presents a novel generative encoding called connective compositional pattern producing Net,works (connective CPPNs) that call effectively detect and capitalize on geometric relationships among sensors and effectors. The key insight is that sensors and effectors with consistent geometric relationships can be exploited by a repeating, motif in the neural architecture. Thus, by employing an encoding that can discover such motifs as a, function of network geometry, it becomes possible to exploit it. In this paper, a method for evolving connective CPPNs called Hypercube-based Neuroevolution, of Augmenting Topologies (HyperNEAT) discovers sensible repeating motifs that take advantage of two different placement schemes, demonstrating the utility of such an approach.

关键词： compositional pattern producing networks NEAT HyperNEAT large-scale artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Motion Evolution of Soft Robot Based on VoxCAD 12th

Research on Motion Evolution of Soft Robot Based on VoxCAD

引用

12th International Conference on Intelligent Robotics and Applications (ICIRA)

作者： Gu, Yueqin Zhang, Xuecheng Wu, Qiuxuan Li, Yancheng Zhang, Botao Gao, Farong Luo, Yanbin Hangzhou Dianzi Univ Hangzhou 310018 Peoples R China Zhejiang Tsinghua Inst Flexible Elect Technol Jiaxing Peoples R China

ISBN: (纸本)9783030275358;9783030275341

The shape changes of soft organisms demonstrate the survival rules in the evolution of self life. It is important for the transform control of soft robots about how to envolve suitable for the shape demands. In this paper, the compositional pattern producing networks (CPPN) algorithm was used to evolve soft robot. By taking simple random functions as genotype inputs, the functions can be weighted combinations to generate the desired phenotype, which mapping relationship between genotypes and phenotypes can be achieved. The VoxCAD simulation software was used to build the three-dimensional topological structure of soft robot and the evolution process of the virtual life was realized by using the specific rule shape to simulate the real environment. The evolutionary analysis of the four-legged walking soft robot was carried out in the simulation experiment, which the effectiveness of the method was verified.

关键词： compositional pattern producing networks VoxCAD Genotype Phenotype Four-legged walking

来源：评论

学校读者我要写书评

暂无评论

Generating Large-Scale Neural networks Through Discovering Geometric Regularities 07

Generating Large-Scale Neural Networks Through Discovering G...

引用

Annual Conference of Genetic and Evolutionary Computation Conference

作者： Gauci, Jason Stanley, Kenneth Univ Cent Florida Sch EECS Evolutionary Complex Res Grp Orlando FL 32836 USA

ISBN: (纸本)9781595936974

Connectivity patterns in biological brains exhibit many repeating motifs. This repetition mirrors inherent geometric regularities in the physical world. For example, stimuli that, excite adjacent locations oil the retina map to neurons that are similarly adjacent in the visual cortex. That way, neural connectivity call exploit geometric locality ill the outside world by employing local connections in the brain. If such regularities could be discovered by methods that evolve artificial neural networks (ANNs), then they could be similarly exploited to solve problems that would otherwise require optimizing too many dimensions to solve. This paper introduces such a method, called Hypercube-based Neuroevolution of Augmenting Topologies (HyperNEAT), which evolves a novel generative encoding called connective compositional pattern producing networks (connective CPPNs) to discover geomertric regularities in the task domain, Connective CPPNs encode connectivity patterns as concepts, that are independent of the number of inputs or out,puts, allowing functional large-scale neural networks to be evolved. In this paper, this approach is tested in a simple visual task for which it effectively discovers the correct underlying regularity, allowing the solution to both generalize scale without loss of function to an ANN of over eight million connections.

关键词： compositional pattern producing networks NEAT HyperNEAT large-scale artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Suitability of Representations for Quality Diversity Optimization of Shapes 23

On the Suitability of Representations for Quality Diversity ...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Scarton, Ludovico Hagg, Alexander Bonn Rhein Sieg Univ Appl Sci St Augustin Germany

ISBN: (纸本)9798400701191

The representation, or encoding, utilized in evolutionary algorithms has a substantial effect on their performance. Examination of the suitability of widely used representations for quality diversity optimization (QD) in robotic domains has yielded inconsistent results regarding the most appropriate encoding method. Given the domain-dependent nature of QD, additional evidence from other domains is necessary. This study compares the impact of several representations, including direct encoding, a dictionary-based representation, parametric encoding, compositional pattern producing networks, and cellular automata, on the generation of voxelized meshes in an architecture setting. The results reveal that some indirect encodings outperform direct encodings and can generate more diverse solution sets, especially when considering full phenotypic diversity. The paper introduces a multi-encoding QD approach that incorporates all evaluated representations in the same archive. Species of encodings compete on the basis of phenotypic features, leading to an approach that demonstrates similar performance to the best single-encoding QD approach. This is noteworthy, as it does not always require the contribution of the best-performing single encoding.

关键词： encoding representation quality diversity compositional pattern producing networks cellular automata parametric

来源：评论

学校读者我要写书评

暂无评论

Generative and developmental systems tutorial 15

Generative and developmental systems tutorial

引用

17th Genetic and Evolutionary Computation Conference, GECCO 2015

作者： Stanley, Kenneth O. Dept. of EECS Computer Science Division University of Central Florida United States

来源：评论

学校读者我要写书评

暂无评论

Research on motion evolution of soft robot based on VoxCAD

Research on motion evolution of soft robot based on VoxCAD

引用

第六届国际仿生工程学术大会暨2019年自然启迪科技国际研讨会

作者： Qiuxuan Wu Xuecheng Zhang Yueqin Gu Rocket Force University of Engineering School of Automation Hangzhou Dianzi University PN Engineering College National University of Sciences and Technology

The soft robot with variable morphology mimics the "survival of the fittest" rule in Darwin's theory of evolution. By using the shape of a specific rule to simulate the display environment, the evolution process of the virtual life is realized. In this paper, the multi-objective combined mode generation network(CPPN-NEAT) algorithm is used to evolve the software robot. By inputting a simple random function as a genotype, the functions can be weighted and combined to generate the desired phenotype and realize the gene. The mapping relationship between type and phenotype is carried out. Then the VoxCAD simulation software is used to build the three-dimensional topology of the software robot, and the simulation analysis is carried out. The software robot with four-legged walking is evolved in the experiment, and the gait is deeply analyzed.

关键词： compositional pattern producing networks VoxCAD Genotype Phenotype Fourlegs Walking

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共1页 << < 1 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：