检索结果-内蒙古大学图书馆

Robots That Think Fast and Slow: An Example of Throwing the Ball Into the Basket

IEEE ACCESS 2016年 4卷 5052-5064页

作者： Li, Tzuu-Hseng S. Kuo, Ping-Huan Ho, Ya-Fang Liu, Chin-Yin Yu, Ting-Chieh Ye, Yan-Ting Chang, Chien-Yu Chen, Guan-Yu Chien, Chih-Wei Chen, Wei-Chung Wu, Li-Fan Fang, Nien-Chu Natl Cheng Kung Univ Tainan 701 Taiwan

Can a robot think like a human being? Scientists in recent years have been trying to achieve this dream, and we are also committed to this same goal. In this paper, we use an example of throwing the ball into the basket to make the robots process with human-like thinking behavior. Such thinking behavior adopted in this paper is divided into two modes: fast and slow. The fast mode belongs to the intuitional reaction, and the slow mode represents the complicated cogitation in human brain. This fascinating human thinking concept is inspired by the book, Thinking, Fast and Slow, which explains the process of the human brain. In addition, the psychology theories proposed in this book are also adopted to realize the thinking algorithms, and our experiments verify that the thinking mode of human beings is reasonable and effective in robots.

关键词： Anchoring effect fast and slow systems FIRA humanoid robot learning algorithm peak-end rule psychology

来源：评论

学校读者我要写书评

暂无评论

Maintaining regularity and generalization in data using the minimum description length principle and genetic algorithm: Case of grammatical inference

引用

SWARM AND EVOLUTIONARY COMPUTATION 2016年 31卷 11-23页

作者： Pandey, Hari Mohan Chaudhary, Ankit Mehrotra, Deepti Kendall, Graham Amity Univ Uttar Pradesh Dept Comp Sci & Engn Sect 125 Noida India Truman State Univ Dept Comp Sci Kirksville MO USA Amity Univ Amity Sch Engn & Technol Sect 125 Noida India Univ Nottigham Malaysia CampusJalan Borga Semenyih 43500 Selangor Darul Malaysia

In this paper, a genetic algorithm with minimum description length (GAWMDL) is proposed for grammatical inference. The primary challenge of identifying a language of infinite cardinality from a finite set of examples should know when to generalize and specialize the training data. The minimum description length principle that has been incorporated addresses this issue is discussed in this paper. Previously, the e-GRIDS learning model was proposed, which enjoyed the merits of the minimum description length principle, but it is limited to positive examples only. The proposed GAWMDL, which incorporates a traditional genetic algorithm and has a powerful global exploration capability that can exploit an optimum offspring. This is an effective approach to handle a problem which has a large search space such the grammatical inference problem. The computational capability, the genetic algorithm poses is not questionable, but it still suffers from premature convergence mainly arising due to lack of population diversity. The proposed GAWMDL incorporates a bit mask oriented data structure that performs the reproduction operations, creating the mask, then Boolean based procedure is applied to create an offspring in a generative manner. The Boolean based procedure is capable of introducing diversity into the population, hence alleviating premature convergence. The proposed GAWMDL is applied in the context free as well as regular languages of varying complexities. The computational experiments show that the GAWMDL finds an optimal or close-to-optimal grammar. Two fold performance analysis have been performed. First, the GAWMDL has been evaluated against the elite mating pool genetic algorithm which was proposed to introduce diversity and to address premature convergence. GAWMDL is also tested against the improved tabular representation algorithm. In addition, the authors evaluate the performance of the GAWMDL against a genetic algorithm not using the minimum description length pr

关键词： Bit-masking oriented data structure Context free grammar Genetic algorithm Grammar induction learning algorithm Minimum description length principle

来源：评论

学校读者我要写书评

暂无评论

An improved maximum spread algorithm with application to complex-valued RBF neural networks

引用

NEUROCOMPUTING 2016年 216卷 261-267页

作者： Liu, Yuanshan Huang, He Huang, Tingwen Qian, Xusheng Soochow Univ Sch Elect & Informat Engn Suzhou 215006 Peoples R China Texas A&M Univ Qatar Doha 5825 Qatar

It has been known that one of the important steps in training a complex-valued radial basis function neural network is to effectively determine its centers and widths of neurons in the hidden layer. In this paper, an improved maximum spread algorithm is propose to solve this issue. Its basic idea is that the choice of centers not only depends on the distances between samples from different classes, but also is heavily affected by the average distance between samples in the same class. The relationship between external and inner distances is taken into account when determining centers. The performance of this algorithm is tested on several datasets. It is shown that much better performance can be achieved by the developed algorithm than by some existing ones. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Complex-valued RBF neural networks learning algorithm Inner distance Classification

来源：评论

学校读者我要写书评

暂无评论

Common Bayesian Network for Classification of EEG-Based Multiclass Motor Imagery BCI

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2016年第6期46卷 843-854页

作者： He, Lianghua Hu, Die Wan, Meng Wen, Ying von Deneen, Karen M. Zhou, MengChu Tongji Univ Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai 201804 Peoples R China Fudan Univ Dept Commun Sci & Engn Shanghai 200433 Peoples R China Minist Educ Ctr Sci & Technol Dev Beijing 100080 Peoples R China E China Normal Univ Dept Comp Sci & Technol Shanghai 200241 Peoples R China Xidian Univ Sch Life Sci & Technol Xian 710071 Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

Modeling and learning of brain activity patterns represent a huge challenge to the brain-computer interface (BCI) based on electroencephalography (EEG). Many existing methods estimate the uncorrelated instantaneous demixing of EEG signals to classify multiclass motor imagery (MI). However, the condition of uncorrelation does not hold true in practice, because the brain regions work with partial or complete collaboration. This work proposes a novel method, termed as a common Bayesian network (CBN), to discriminate multiclass MI EEG signals. First, with the constraints of a Gaussian mixture model on every channel, only related channels are selected to construct a normal Bayesian network. Second, the nodes that have both common and varying edges are selected to construct a CBN. Third, the probabilities on common edges are used to learn about the support vector machine for classification. To validate the proposed method, we conduct experiments on two well-known BCI datasets and perform a numerical analysis of the propose algorithm for EEG classification in a multiclass MI BCI. Experimental results show that the proposed CBN method not only has excellent classification performance, but also is highly efficient. Hence, it is suitable for the cases where a system is required to respond within a second.

关键词： Bayesian network (BN) brain-computer interface (BCI) electroencephalography (EEG) learning algorithm support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Bivariate fully fuzzy interpolation problem using artificial neural networks approach

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2016年第4期30卷 2267-2275页

作者： Hosseini, E. Jafarian, A. Islamic Azad Univ Dept Math Urmia Branch Orumiyeh Iran

Artificial neural networks modeling is one of the most prominent techniques for solving more complicated mathematical problems that can not be solved in the traditional computing environments. The work described here intends to offer an efficient bivariate fuzzy interpolation methodology based on the artificial neural networks approach. It has several notable features including high processing speeds and the ability to learn the solution to a problem from a set of examples which categorizes them in line of intelligent systems. To do this, a multilayer feed-forward neural architecture is depicted for constructing a fully fuzzy interpolating polynomial of arbitrary degree. Then, a back-propagation supervised learning optimization algorithm will be applied for estimating the unknown fuzzy coefficients of the solution polynomial. Finally, the advantage of our technique is illustrated by using some practical examples to show the ability of the improved algorithm in solving rigorous problems.

关键词： Bivariate fully fuzzy polynomial artificial neural network approximate solution criterion function learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Sleeping experts and bandits approach to constrained Markov decision processes

引用

AUTOMATICA 2016年 63卷 182-186页

作者： Chang, Hyeong Soo Sogang Univ Dept Comp Sci & Engn Seoul South Korea

This communique presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for "sleeping experts and bandits" problem and their computational complexities are independent of state and action space sizes if the given policy set is relatively small. We establish convergence of their expected performances to the value of an optimal policy and convergence rates, and also almost-sure convergence to an optimal policy with an exponential rate for the algorithm adapted within the context of sleeping experts. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Markov decision processes Sleeping experts and bandits learning algorithm Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Data Association via Logistic Regression Model for Multiple Target Tracking Problems 20

Data Association via Logistic Regression Model for Multiple ...

引用

20th International Conference on Information Fusion (Fusion)

作者： Chen, Chen Zhou, Jie Sichuan Univ Coll Math Chengdu 610064 Sichuan Peoples R China

ISBN: (纸本)9780996452700

In the multiple target tracking scenarios, the correct matching between targets and measurements is critical. There have been many approaches to resolve this problem called data association. In this paper, a regression method is proposed to resolve the data association problem. In the logistic regression model, nine potential predictor variables are designed which are related to the geometric information of measurements and estimated states of multiple targets, including the distance, intersection angle of position vectors and smoothness of tracks at current time instant and several previous time steps, and the dependent variable is the association probability of matching the measurement with all targets. The regression coefficients are trained through a designed multiple target tracking system. For the new unknown tracking systems with the given number of tracked targets, the measurement having the highest association probability with a target is considered as the true measurement about such target using the trained empirical regression model. Moreover, various filtering algorithms can be invoked to tracking targets. Simulation studies show the proposed novel mechanism for tackling with data association problem in multiple target tracking is effective.

关键词： Data Association multiple target tracking logistic regression learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Predictive modelling of the LD₅₀ activities of coumarin derivatives using neural statistical approaches: Electronic descriptor-based DFT

引用

JOURNAL OF TAIBAH UNIVERSITY FOR SCIENCE 2016年第4期10卷 451-461页

作者： Hmamouchi, Rachid Larif, Majdouline Chtita, Samir Adad, Azeddine Bouachrine, Mohammed Lakhlifi, Tahar Univ Moulay Ismail Fac Sci Mol Chem & Nat Subst Lab Meknes Morocco Univ Ibn Tofail Fac Sci Separat Proc Labs Kenitra Morocco Univ Moulay Ismail ESTM Meknes Morocco

A study of structure-activity relationship (QSAR) was performed on a set of 30 coumarin-based molecules. This study was performed using multiple linear regressions (MLRs) and an artificial neural network (ANN). The predicted values of the antioxidant activities of coumarins were in good agreement with the experimental results. Several statistical criteria, such as the mean square error (MSE) and the correlation coefficient (R), were studied to evaluate the developed models. The best results were obtained with a network architecture [8-4-1] (R = 0.908, MSE = 0.032), activation functions (tansig-purelin) and the Levenberg-Marquardt learning algorithm. The model proposed in this study consists of large electronic descriptors that are used to describe these molecules. The results suggested that the proposed combination of calculated parameters may be useful for predicting the antioxidant activities of coumarin derivatives. (C) 2015 The Authors. Production and hosting by Elsevier B.V. on behalf of Taibah University.

关键词： Predicted QSAR MLR ANN learning algorithm Levenberg-Marquardt

来源：评论

学校读者我要写书评

暂无评论

Application of Optimized Neural Network in Data Processing

Application of Optimized Neural Network in Data Processing

引用

作者： Jianjun WU Hunan City University

As the ART2 neural network clustering occurs normalization in the data inputting mode by vector and nonlinear transformation pretreatment process is easy to be filtered as a substrate for an important, but a minor component of the noise, while there are still phenomenon of the drifting mode in the learning process due to the correction of the value of weight, this paper proposes an improved method of ART2 neural network. The improved method stores the amplitude information in the learning process, and it is considering the shortest distance of being inputted into the center of the cluster, increasing a threshold limit value for determining outliers at the same time and eliminating the influence of outliers of the clustering results. Finally, the clustering of data samples experimental results show that: the improved ART2 network can handle negative data, the four quadrants of data can be effectively clustered, the performance is superior to the traditional ART2 network.

关键词： Adaptive resonance learning algorithm Neurons Resonance

来源：评论

学校读者我要写书评

暂无评论

learning Fuzzy Cognitive Maps Using Decomposed Parallel Ant Colony algorithm and Gradient Descent 12

Learning Fuzzy Cognitive Maps Using Decomposed Parallel Ant ...

引用

12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Ye, Nan Zhang, Rongwei Yu, Kena Wang, Dehong Ningbo Power Supply Co State Grid Zhejiang Elect Power Co Ningbo Zhejiang Peoples R China Ningbo Lijian Transportat Infrastruct & Project C Ningbo Zhejiang Peoples R China

ISBN: (纸本)9781467376822

Fuzzy cognitive maps (FCMs) are a model for causal modeling and causal inference. It represents the real-world concepts and the causal relations between the concepts by using fuzzy variables. The major benefit of the fuzzy variables is that the model is more robust to the errors in the observed data. Although FCMs have been widely used in different research areas, it is still an open problem to efficiently construct large scale FCM models. To further improve the efficiency of the existing FCM learning algorithms, we propose a new algorithm that combines ant colony optimization algorithm, gradient descent local search and a decomposed parallel computing framework to build large scale FCMs from observational data. A set of network inference problem is used to evaluate the performance of the proposed algorithm and the results are compared to other algorithms including traditional ant colony optimization, and real coded genetic algorithms. Experimental results suggest that our algorithm outperforms the other algorithms in terms of model accuracy. We also compared the computation time required by the non-parallel ant colony optimization algorithm and the proposed parallel algorithm. When the number of nodes is appropriate, the speedup could be very close to linear speedup.

关键词： fuzzy cognitive map ant colony optimization learning algorithm decomposed framework parrallel computing

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：