NEAT
NEAT的相关文献在2003年到2022年内共计101篇,主要集中在自动化技术、计算机技术、一般工业技术、教育
等领域,其中期刊论文91篇、专利文献10篇;相关期刊31种,包括考试与评价(英语人教新课标高二版)、考试与评价(英语新目标八年级版)、考试与评价(英语新目标七年级版)等;
NEAT的相关文献由94位作者贡献,包括齐法鸿、齐飞、万小泉等。
NEAT
-研究学者
- 齐法鸿
- 齐飞
- 万小泉
- 沈建林
- J-C·马林
- L·斯坦德尔特
- 丁劲
- 刘娜
- 史伟云
- 周庆军
- 姜慧
- 孙文
- 张彬
- 曲乐
- 李晓峰
- 李飞
- 杨志梅
- 王安新
- 王林辉
- 王红阳
- 王群
- 王雪
- 窦圣乾
- 陈忠富
- 陈程
- 齐瑞平
- Bidyut Gupta
- Guillaume Redler
- Hiroyuki Ito
- Kenji Funaki
- Mizuho Taguchi
- Motoyoshi Noike
- Risehiro Nonaka
- Sayaka Sato
- Shahram Rahimi
- Shinji Ishizuka
- Shoko Suzuki
- Soroosh Sohangir
- Taisei Kagaya
- Takeshi Kodama
- Yasuo Yokoyama
- 丁继明
- 乜铁建
- 于家懿
- 付新
- 倪群
- 刘丽华
- 刘婷婷
- 刘箴
- 刘赫
-
-
司徒1;
小路(图)1
-
-
摘要:
音响之道在于搭配无论是刚入门的玩家,还是老烧友,一定会了解音响之道在于搭配。不同的产品之间的搭配,会搭配出不同的效果,至于是否合适,除了要看顾客的□味之外,还需要店家、代理商对拥有的品牌和产品进行深入了解之后作出的配搭。
-
-
Shoko Suzuki;
Hiroyuki Ito;
Shinji Ishizuka;
Risehiro Nonaka;
Motoyoshi Noike;
Takeshi Kodama;
Kenji Funaki;
Mizuho Taguchi;
Taisei Kagaya;
Sayaka Sato;
Guillaume Redler;
Yasuo Yokoyama
-
-
摘要:
In the field of organic syntheses, the development of environmentally friendly methods based on the concept of green chemistry has been always required. In response to this requirement, we reported solvent- and catalyst-free syntheses of imines using the pressure reduction technique as a key technology. We found that this reaction proceeded very rapidly in the initial stage, but its rate decreased with the passage of time. It was also found that the reaction of benzaldehyde with aniline had a specificity that the phase transition occurred. In this method, the desired imines could be obtained in good to excellent yields, but target compounds had to be given by purifications using organic solvents. Therefore, we tried to develop the perfect synthetic method of imine derivatives without organic or inorganic solvents. We selected two methods and took them into this investigation. One was exactly mixing (1:1, substance ratio) aldehydes and amines and the other was employing lower pressure (>0.1 mmHg, previous method: 1.0 mmHg) at the pressure reducing technique. When this improved synthetic method was performed, it was revealed that pure target imines were obtained in excellent yields without any purification.
-
-
吴雷;
刘箴;
钱平安;
刘婷婷;
王瑾;
柴艳杰
-
-
摘要:
针对非结构化、未知环境下的智能体路径规划问题,提出了一种基于增强拓扑神经进化(Neuro-Evolution of Augmenting Topologies)的方法.通过对智能体进行仿真建模,为智能体提供感知模型和记忆模型,将感知模型和记忆模型的数值作为神经网络的输入来指导智能体在仿真环境中的行为.设定合理的适应性函数,对智能体在仿真环境中执行路径规划任务的表现进行评价.通过NEAT算法对指导智能体行为的神经网络进行结构和权值优化,并生成一个最佳神经网络.仿真实验显示,基于NEAT算法进化出的神经网络,可以指导智能体快速地寻找到一条有效路径.
-
-
-
-
-
Soroosh Sohangir;
Shahram Rahimi;
Bidyut Gupta
-
-
摘要:
The larger the size of the data, structured or unstructured, the harder to understand and make use of it. One of the fundamentals to machine learning is feature selection. Feature selection, by reducing the number of irrelevant/redundant features, dramatically reduces the run time of a learning algorithm and leads to a more general concept. In this paper, realization of feature selection through a neural network based algorithm, with the aid of a topology optimizer genetic algorithm, is investigated. We have utilized NeuroEvolution of Augmenting Topologies (NEAT) to select a subset of features with the most relevant connection to the target concept. Discovery and improvement of solutions are two main goals of machine learning, however, the accuracy of these varies depends on dimensions of problem space. Although feature selection methods can help to improve this accuracy, complexity of problem can also affect their performance. Artificialneural networks are proven effective in feature elimination, but as a consequence of fixed topology of most neural networks, it loses accuracy when the number of local minimas is considerable in the problem. To minimize this drawback, topology of neural network should be flexible and it should be able to avoid local minimas especially when a feature is removed. In this work, the power of feature selection through NEAT method is demonstrated. When compared to the evolution of networks with fixed structure, NEAT discovers significantly more sophisticated strategies. The results show NEAT can provide better accuracy compared to conventional Multi-Layer Perceptron and leads to improved feature selection.
-
-
-