检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Boris Kovalerchuk Dept. of Computer Science Central Washington University

ISBN: (纸本)9781509006212

Fundamental challenges and goals of the cognitive algorithms are moving super-intelligent machines and super-intelligent humans from dreams to reality. This paper is devoted to a technical way to reach some specific aspects of super-intelligence that are beyond the current human cognitive abilities. Specifically the proposed technique is to overcome inabilities to analyze a large amount of abstract numeric high-dimensional data and finding complex patterns in these data with a naked eye. Discovering patterns in multidimensional data using visual means is a long-standing problem in multiple fields and Data Science and Modeling in general. The major challenge is that we cannot see n-D data by a naked eye and need visualization tools to represent n-D data in 2-D losslessly. The number of available lossless methods is quite limited. The objective of this paper is expanding the class of such lossless methods, by proposing a new concept of Generalized Shifted Collocated Paired Coordinates. The paper shows the advantages of proposed lossless technique by proving mathematical properties and by demonstration on real data.

关键词： High-dimensional data High-dimensional patterns Lossless representation Generalized coordinates cognitive algorithms Human cognitive abilities Super-intelligence generalized coordinates Lossless dimensional data visual representation Dreams

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired algorithms in Data Management Processes 10

Bio-inspired Algorithms in Data Management Processes

引用

10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing 3PGCIC

作者： Ogiela, Lidia Ogiela, Marek R. AGH Univ Sci & Technol Fac Management 30 Mickiewicza Ave PL-30059 Krakow Poland AGH Univ Sci & Technol Cryptog & Cognit Informat Res Grp PL-30059 Krakow Poland

ISBN: (纸本)9781467394734

In this paper will be describe the bio-inspired and personal interpretation algorithms. These algorithms are based on biometrics and individual characteristics features. These algorithms will be dedicated for data analysis processes and data management support. Also cognitive aspects of data analysis processes will be shown in this paper. The data analysis aspects will be described by individual/ personal algorithms and cognitive aspects.

关键词： personal interpretation algorithms data management cognitive algorithms

来源：评论

学校读者我要写书评

暂无评论

Non-Supervised Rule for Direct Sequence Spread Spectrum Signal Sequence Acquisition 9

Non-Supervised Rule for Direct Sequence Spread Spectrum Sign...

引用

International Conference on Broadband and Wireless Computing, Communication and Applications (BWCCA)

作者： Cheng, Hao Luo, Zhenghua Sun, Guolin Chengdu Univ Telecommun Engn Lab Chengdu Peoples R China Univ Elect Sci & Technol Comp Lab Chengdu Peoples R China

ISBN: (纸本)9781479941735

Having not the apriority knowledge about the DSSS signal in the non-cooperation condition, we proposed a Non-Supervised neural network algorithm to detect and identify the PN sequence. A cognitive learning algorithms for estimation the direct sequence spread spectrum (DSSS) signal pseudo-noise (PN) sequence is presented. The non-supervised learning algorithm is proposed according to the Kohonen rule in SOFM. The blind algorithm can also estimation the PN sequence in low SNR and computer simulation demonstrated that the algorithm is effective. Comparing the traditional algorithm based on slip-correlation, the cognitive algorithm's bit error rate(BER) and complexity is lower.

关键词： cognitive algorithms non-supervised learning blind estimation DSSS signal PN sequence

来源：评论

学校读者我要写书评

暂无评论

Improved Natural Gradient algorithms for Multi-channel Signal Separation 3

Improved Natural Gradient Algorithms for Multi-channel Signa...

引用

3rd International Conference on Advanced Engineering Materials and Architecture Science (ICAEMAS)

作者： Hao, Cheng Na, Yu Jun, Liu Chengdu Univ Telecommun Engn Coll Chengdu Sichuan Peoples R China Univ Elect Sci & Technol Natl Key Lab Commun Chengdu Sichuan Peoples R China

ISBN: (纸本)9783038352679

In this paper, an Multi-channel blind separation of Direct Sequence Code Division Multiple Access (DS-CDMA) has been introduced. Most of which we assume statistically stationary sources as well as instantaneous mixtures of signals using blind source separation (BSS) algorithms. In practicality, the CDMA sources received are convolute mixing. A more complex blind separation algorithm is required to achieve better source separation. Based on the minimizing the average squared cross-output-channel-correlation, the proposed scheme obtains the better source separation. Simulation results show that the proposed optimal scheme not only achieves superior bit error rate (BER) performance to those of the existing ones, but also provides a guaranteed-convergent solution under different channel conditions.

关键词： cognitive algorithms Natural Gradient DS-CDMA Pseudo-Random Sequences Multi-channel Separation

来源：评论

学校读者我要写书评

暂无评论

cognitive dynamic logic algorithms for situational awareness

Cognitive dynamic logic algorithms for situational awareness

引用

Conference on Evolutionary and Bio-Inspired Computation - Theory and Applications IV

作者： Perlovsky, L. I. Ilin, R. Harvard Univ 80 Scott Dr Hanscom AFB MA 01731 USA US Air Force Res Lab Hanscom AFB MA 01731 USA

ISBN: (纸本)9780819481689

Autonomous situational awareness (SA) requires an ability to learn situations. It is mathematically difficult because in every situation there are many objects nonessential for this situation. Moreover, most objects around are random, unrelated to understanding contexts and situations. We learn in early childhood to ignore these irrelevant objects effortlessly, usually we do not even notice their existence. Here we consider an agent that can recognize a large number of objects in the world;in each situation it observes many objects, while only few of them are relevant to the situation. Most of situations are collections of random objects containing no relevant objects, only few situations "make sense," they contain few objects, which are always present in these situations. The training data contains sufficient information to identify these situations. However, to discover this information all objects in all situations should be sorted out to find regularities. This "sorting out" is computationally complex;its combinatorial complexity exceeds by far all events in the Universe. The talk relates this combinatorial complexity to Godelian limitations of logic. We describe dynamic logic (DL) that quickly learns essential regularities-relevant, repeatable objects and situations. DL is related to mechanisms of the brain-mind and we describe brain-imaging experiments that have demonstrated these relations.

关键词： cognitive algorithms situational awareness complexity logic Godel dynamic logic learning

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Investigation of a Neocortex Model Implementation on the Cray XD1 07

A Preliminary Investigation of a Neocortex Model Implementat...

引用

ACM/IEEE SC07 Conference

作者： Rice, Kenneth L. Vutsinas, Christopher N. Taha, Tarek M. Clemson Univ Dept Elect & Comp Engn Clemson SC 29634 USA

ISBN: (纸本)9781595939746

In this paper we study the acceleration of a new class of cognitive processing applications based on the structure of the neocortex. Specifically we examine the speedup of a visual cortex model for image recognition. We propose techniques to accelerate the application on general purpose processors and on reconfigurable logic. We present implementations of our approach on a Cray XD1 and compare the performance potential of scaling the design utilizing reconfigurable logic based acceleration to a software only design. Our results indicate that acceleration using reconfigurable logic can provide a significant speedup over a software only implementation.

关键词： Reconfigurable cognitive algorithms application performance FPGA

来源：评论

学校读者我要写书评

暂无评论

Scaling analysis of a neocortex inspired cognitive model on the Cray XD1

引用

JOURNAL OF SUPERCOMPUTING 2009年第1期47卷 21-43页

作者： Rice, Kenneth L. Taha, Tarek M. Vutsinas, Christopher N. Clemson Univ Dept Elect & Comp Engn Clemson SC 29634 USA

This paper presents the implementation and scaling of a neocortex inspired cognitive model on a Cray XD1. Both software and reconfigurable logic based FPGA implementations of the model are examined. This model belongs to a new class of biologically inspired cognitive models. Large scale versions of these models have the potential for significantly stronger inference capabilities than current conventional computing systems. These models have large amounts of parallelism and simple computations, thus allowing highly efficient hardware implementations. As a result, hardware-acceleration of these models can produce significant speedups over fully software implementations. Parallel software and hardware-accelerated implementations of such a model are investigated for networks of varying complexity. A scaling analysis of these networks is presented and utilized to estimate the throughput of both hardware-accelerated and software implementations of larger networks that utilize the full resources of the Cray XD1. Our results indicate that hardware-acceleration can provide average throughput gains of 75 times over software-only implementations of the networks we examined on this system.

关键词： Reconfigurable computing cognitive algorithms Performance scaling Parallel computing

来源：评论

学校读者我要写书评

暂无评论

A cognitive Mechanism for Rate Adaptation in Wireless Networks

A Cognitive Mechanism for Rate Adaptation in Wireless Networ...

引用

4th IEEE International Workshop on Modelling Autonomic Communications Environments

作者： Chaves, Luciano Malheiros, Neumar Madeira, Edmund Garcia, Islene Kliazovich, Dzmitry Univ Estadual Campinas Inst Comp Av Albert Einstein 1271 Iwaki Fukushima 13083970 Japan Univ Trent Via Sommarive 14 I-38050 Trento Italy

ISBN: (纸本)9783642050053

Sophisticated wireless interfaces support multiple transmission data rates and the selection of the optimal data rate has a critical impact on the overall network performance. Proper rate adaptation requires dynamically adjusting data rate based on current channel conditions. Despite several rate adaptation algorithms have been proposed in the literature, there are still challenging issues related to this problem. The main limitations of current solutions are concerned with how to estimate channel quality to appropriately adjust the rate. In this context, we propose a cognitive Rate Adaptation mechanism for wireless networks. This mechanism includes a distributed self-configuration algorithm in which the selection of data rate is based on past experience. The proposed approach can react to changes in channel conditions and converge to the optimal data rate, while allowing a fair channel usage among network nodes. Simulation results obtained underline performance benefits with respect to existing rate adaptation algorithms.

关键词： Wireless Networks Rate Adaptation Self-configuration Self-optimization cognitive algorithms

来源：评论

学校读者我要写书评

暂无评论

From Auto-adaptive to Survivable and Self-Regenerative Systems - Successes, Challenges, and Future

From Auto-adaptive to Survivable and Self-Regenerative Syste...

引用

8th IEEE International Symposium on Network Computing and Applications

作者： Atighetchi, Michael Pal, Partha BBN Technol Informat & Knowledge Technol Business Unit Cambridge MA USA

ISBN: (纸本)9781424446445

This paper charts the course of adaptive behavior in intrusion tolerance, starting from pre-programmed and user-controlled reactive adaptation to highly sophisticated autonomic and cognitively driven adaptation. The goal of intrusion-tolerance is to provide mission continuity even under conditions of sustained cyber attacks. We describe key themes of our previous work in adaptive cyber defense and introduction of autonomic response capabilities and discuss challenges that warrant further research. We also discuss the potential impact of new trends in distributed systems, e.g., service-oriented architecture and cloud computing, on future survivable systems, and point out new opportunities for developing sophisticated auto-adaptive capabilities for increased survivability.

关键词： Intrusion Tolerance Information Assurance Survivability cognitive algorithms Autonomous Computing

来源：评论

学校读者我要写书评

暂无评论

Simulation of a cognitive algorithm for a distributed robotic sensing network

Simulation of a cognitive algorithm for a distributed roboti...

引用

5th Biannual World Automation Congress

作者： Schoenwald, D Xavier, P Thomas, E Forsythe, C Parker, E Sandia Natl Labs Albuquerque NM 87185 USA

ISBN: (纸本)1889335193

This paper presents simulation and analysis of a collective Of autonomous unmanned ground-based vehicles navigating a building searching for increasing smoke concentrations. The vehicles communicate smoke concentrations to each other to determine the location of the highest concentration value. The data generated from the robots' sensors is used to activate a semantic network to generate data for further cognitive operations. Statistical analysis is employed on the data to identify schema and themes, which enable the robots to convey a story of their experiences, thus emulating human episodic memory.

关键词： modeling & simulation autonomous robotic vehicles cognitive algorithms distributed network human cognitive emulation

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：