免疫进化子波网络及其学习算法

本文首次对子波神经网络的分类机理进行了详细地研究,在此基础上将免疫进化算法与子波神经网络相集成,并提出了免疫进化子波网络模型及其学习算法.其中,免疫进化算法是一种集免疫机制和进化机制于一体的一种新的全局并行算法,它可以通过对进化环境的自适应和自学习,有针对性地抑制由原进化算子操作的盲目性而引起的退化现象.理论分析和用于双螺旋线分类的仿真结果表明,免疫进化子波网络不仅是可行的,也是十分有效的.由于免疫进化算法本身所固有的并行运算规则、智能搜索方式和概率判断准则,从而有利于弱化子波网络的应用条件,加强其联想记忆和信息处理的能力.     

球类运动中人体姿态估计研究进展

针对单个RGB图像,人体姿态估计通过对人体关键点定位来估计人体的位置和关节点位置。球类比赛是一种快速的运动,用主观观察对运动员的技术合法性进行判决无法避免错误。因此,文中利用基于人体姿态估计的运动员姿态分析技术进行辅助训练和辅助判罚,有效避免了传统系统中由于人的主观判断对运动员姿态的错误定位。目前,针对人体姿态估计的研究被分为基于传统算法和基于深度学习算法两种主要方式。在基于深度学习算法的基础上又分为单人人体姿态检测和多人人体姿态检测。基于深度学习算法的人体姿态估计通过构建神经网络,运用机器学习的方法提取图片特征读取图片信息,并在用于人体姿态估计的主流数据集上进行性能对比和分析。将人体姿态估计应用到球类运动中,为运动员的日常训练提供了一定的科学参考,同时也最大程度上保证了运动员比赛中的公平与公正。     

A QoS-provisioning neural fuzzy connection admission controller formultimedia high-speed networks

This paper proposes a neural fuzzy approach for connection admission control (CAC) with QoS guarantee in multimedia high-speed networks. Fuzzy logic systems have been successfully applied to deal with traffic-control-related problems and have provided a robust mathematical framework for dealing with real-world imprecision. However, there is no clear and general technique to map domain knowledge on traffic control onto the parameters of a fuzzy logic system. Neural networks have learning and adaptive capabilities that can be used to construct intelligent computational algorithms for traffic control. However, the knowledge embodied in conventional methods is difficult to incorporate into the design of neural networks. The proposed neural fuzzy connection admission control (NFCAC) scheme is an integrated method that combines the linguistic control capabilities of a fuzzy logic controller and the learning abilities of a neural network. It is an intelligent implementation so that it can provide a robust framework to mimic experts' knowledge embodied in existing traffic control techniques and can construct efficient computational algorithms for traffic control. We properly choose input variables and design the rule structure for the NFCAC controller so that it can have robust operation even under dynamic environments. Simulation results show that compared with a conventional effective-bandwidth-based CAC, a fuzzy-logic-based CAC, and a neural-net-based CAC, the proposed NFCAC can achieve superior system utilization, high learning speed, and simple design procedure, while keeping the QoS contract     

A Hybrid of Cooperative Particle Swarm Optimization and Cultural Algorithm for Neural Fuzzy Networks and Its Prediction Applications

This study presents an evolutionary neural fuzzy network, designed using the functional-link-based neural fuzzy network (FLNFN) and a new evolutionary learning algorithm. This new evolutionary learning algorithm is based on a hybrid of cooperative particle swarm optimization and cultural algorithm. It is thus called cultural cooperative particle swarm optimization (CCPSO). The proposed CCPSO method, which uses cooperative behavior among multiple swarms, can increase the global search capacity using the belief space. Cooperative behavior involves a collection of multiple swarms that interact by exchanging information to solve a problem. The belief space is the information repository in which the individuals can store their experiences such that other individuals can learn from them indirectly. The proposed FLNFN model uses functional link neural networks as the consequent part of the fuzzy rules. This study uses orthogonal polynomials and linearly independent functions in a functional expansion of the functional link neural networks. The FLNFN model can generate the consequent part of a nonlinear combination of input variables. Finally, the proposed FLNFN with CCPSO (FLNFN-CCPSO) is adopted in several predictive applications. Experimental results have demonstrated that the proposed CCPSO method performs well in predicting the time series problems.     

A self-learning evolutionary chess program

A central challenge of artificial intelligence is to create machines that can learn from their own experience and perform at the level of human experts. Using an evolutionary algorithm, a computer program has learned to play chess by playing games against itself. The program learned to evaluate chessboard configurations by using the positions of pieces, material and positional values, and neural networks to assess specific sections of the chessboard. During evolution, the program improved its play by almost 400 rating points. Testing under simulated tournament conditions against Pocket Fritz 2.0 indicated that the evolved program performs above the master level.     

Evolutionary fuzzy neural networks for hybrid financial prediction

In this paper, an evolutionary fuzzy neural network using fuzzy logic, neural networks (NNs), and genetic algorithms (GAs) is proposed for financial prediction with hybrid input data sets from different financial domains. A new hybrid iterative evolutionary learning algorithm initializes all parameters and weights in the five-layer fuzzy NN, then uses GA to optimize these parameters, and finally applies the gradient descent learning algorithm to continue the optimization of the parameters. Importantly, GA and the gradient descent learning algorithm are used alternatively in an iterative manner to adjust the parameters until the error is less than the required value. Unlike traditional methods, we not only consider the data of the prediction factor, but also consider the hybrid factors related to the prediction factor. Bank prime loan rate, federal funds rate and discount rate are used as hybrid factors to predict future financial values. The simulation results indicate that hybrid iterative evolutionary learning combining both GA and the gradient descent learning algorithm is more powerful than the previous separate sequential training algorithm described in.     

数据挖掘中分类方法的研究

分类是数据挖掘中的最重要的技术之一。目前实现分类的方法有统计方法、机器学习方法和人工智能方法等，常用的技术有决策树分类、贝叶斯分类、神经网络分类等。通过对当前具有代表性的分类算法原理进行分析、比较，总结出每种算法的性能特征，既便于使用者了解掌握各种分类算法、更好地选择合适的算法，又便于研究者对算法进行研究改进，提出性能更好的分类算法。     

基于卷积神经网络的《黑暗之魂》游戏AI设计

近年来,电子游戏成为受广大年轻人喜爱的娱乐方式,而游戏开发者们也试图将人工智能,机器学习的研究成果应用于游戏产业。具体就体现在游戏人物的行为逻辑、游戏难度曲线自适应等方面。让虚拟角色的行为看起来更加接近于智慧生物。从而为玩家带来更好的代入感和成就感。对于游戏中画面数据的训练,我们使用了对于图像数据效果好的卷积神经网络模型,并改进了数据科学领域广泛应用的AlexNet。从而实现了模型训练效果的高效准确。通过FROM SOFTWARE开发的广受好评的动作角色扮演游戏《黑暗之魂》为例,展示如何利用深度学习技术让角色实现自动化和自适应的攻击与防御,塑造更加接近于人类行为的虚拟角色。     

Repeated game theory as a framework for algorithm development in communication networks

This article presents a tutorial on how to use repeated game theory as a framework for algorithm development in communication networks. The article starts by introducing the basis of one‐stage games and how the outcome of such games can be predicted, through iterative elimination and Nash equilibrium. In communication networks, however, not all problems can be modeled using one‐stage games. Some problems can be better modeled through multi‐stage games, as many problems in communication networks consist of several iterations or decisions that need to be made over time. Of all the multi‐stage games, the infinite‐horizon repeated games were chosen to be the focus in this tutorial, because optimal equilibrium settings can be achieved, contrarily to the suboptimal equilibria achieved in other types of game. With the theoretical concepts introduced, it is then shown how the developed game theoretical model, and devised equilibrium, can be used as a basis for the behavior of an algorithm, which is supposed to solve a particular problem and will be running at specific network devices. Copyright © 2015 John Wiley & Sons, Ltd.     

神经网络在ATM流量控制中的应用

以ATM流量控制的三层结构模型为基础，介绍神经网络在接入允许控制（CAC）中的五种算法——学习控制方法、hybrid允许方法、移动窗口训练方法，BPHT算法和时间-差分学习方法。讨论基于神经网络的流量测量、流量管理和拥塞控制方法。性能分析结果表明神经网络提供了快速、自适应、简单的智能控制。     

Understanding representational sensitivity in the iterated prisoner's dilemma with fingerprints

The iterated prisoner's dilemma is a widely used computational model of cooperation and conflict. Many studies report emergent cooperation in populations of agents trained to play prisoner's dilemma with an evolutionary algorithm. This study varies the representation of the evolving agents resulting in levels of emergent cooperation ranging from 0% to over 90%. The representations used in this study are directly encoded finite-state machines, cellularly encoded finite-state machines, feedforward neural networks, if-skip-action lists, parse trees storing two types of Boolean functions, lookup tables, Boolean function stacks, and Markov chains. An analytic tool for rapidly identifying agent strategies and comparing across representations called a fingerprint is used to compare the more complex representations. Fingerprints provide functional signatures of an agent's strategy in a manner that is independent of the agent's representation. This study demonstrates conclusively that choice of a representation dominates agent behavior in evolutionary prisoner's dilemma. This in turn suggests that any soft computing system intended to simulate behavior must be concerned with the representation issue.     

边缘环境下的视频行为识别

边缘智能是一种新兴的智能计算模式,其将人工智能技术和边缘嵌入式设备结合,被广泛应用于物联网系统。智能摄像机是典型的边缘设备之一,它能提供低延迟的视频处理能力,适用于智能家居、智能交通、智能监控等领域。然而,由于摄像机的计算资源有限,传统的行为识别模型难以在本地完成计算任务。为解决这一问题,文中提出了一种基于边缘计算的架构,利用深度学习目标检测算法YOLO v3对视频行为进行识别。在该架构中,智能移动终端负责数据采集和压缩,边缘服务器承担大部分目标检测任务,而检测困难的目标和模型训练则由云服务器负责。为更好地适应边缘设备,本文采用轻量化的神经网络MobileNet替换YOLO v3模型的特征提取模块。经过测试,该架构能有效提取和识别视频中的静态和动态行为,为实现边缘计算环境下低成本、大规模的行为识别提供了有益的参考。     

进化神经网络间接编码方法的计算框架研究

针对传统的直接编码方法对大规模神经网络难以进化的问题,研究者提出了进化神经网络的间接编码方法,这类方法的核心思想是网络子结构的重复可通过一组基因的多次表达来实现从基因型到表现型的映射,这种基因重用机制可在较小的基因空间中进行大规模神经网络的快速搜索.本文在总结和分析各类间接编码实现方法的基础上,给出了进化神经网络间接编码方法的一般性计算框架,每一次神经网络的进化过程分为三个阶段:发育阶段、学习阶段和进化阶段.并从计算框架的基因组进化过程和神经网络发育过程两个方面比较分析了各种典型间接编码方法的优缺点.     

Fuzzy stack filters-their definitions, fundamental properties, andapplication in image processing

A new fuzzy filter, called fuzzy stack filter (FSF), is proposed to extend the filtering capability of conventional stack filter (SF), which is based on the positive Boolean function (PBF) as its window operator. We fuzzify the onset and off-set of a given PBF to obtain two types of fuzzy PBFs. Then, we adopt the architecture of threshold decomposition to develop this new fuzzy filter with a fuzzy PBF as its window operator. Each fuzzy PBF is associated with a set of control parameters. Therefore, the original PBF can be estimated from above and below by two fuzzy PBFs with appropriate control parameters. Furthermore, we can apply the fuzzy modifiers to modify the fuzzy PBFs such that the PBFs can be completely estimated by the fuzzy PBFs. Hence, the stack filter is a special case of fuzzy stack filter. Since some control parameters are added in this new filter, the neural learning algorithms can be easily developed under the flexibility of the given control parameters. We first propose the fuzzy (m,n) rank-order filter to test our proposed learning algorithm. In this simple learning algorithm, we can remove the noise-corrupted images very well in contrast to the filtering behavior of rank-order filters. We believe that the results presented will lead to more fruitful research on more advanced and powerful learning algorithms dedicated to the appropriate applications.     

一个基于随机神经网络的信息传输系统模型及其实现

提出了一个基于随机三层前向网络的信息传输系统（ITS）模型。在此系统框架下，把编码、信道与译码统一考虑，设计系统完成信息的智能传输。与传统的编译码相比，该模型具有很大的通用情形与自适应性。通过把BP算法引入随机神经元的学习，从而推出信息传输系统的学习算法（ITBP）。对于二进对称信道传输仿真结果表明了此模型的有效性及特点。     

Bio-Interactive Healthcare Service System Using Lifelog Based Context Computing

Intelligent bio-sensor information processing was developed using lifelog based context aware technology to provide a flexible and dynamic range of diagnostic capabilities to satisfy healthcare requirements in ubiquitous and mobile computing environments. To accomplish this, various noise signals were grouped into six categories by context estimation and effectively reconfigured noise reduction filters by neural network and genetic algorithm. The neural network-based control module effectively selected an optimal filter block by noise context-based clustering in running mode, and filtering performance was improved by genetic algorithm in evolution mode. Due to its adaptive criteria, genetic algorithm was used to explore the action configuration for each identified bio-context to implement our concept. Our proposed Bio-interactive healthcare service system adopts the concepts of biological context-awareness with evolutionary computations in working environments modeled and identified as bio-sensors based environmental contexts. We used an unsupervised learning algorithm for lifelog based context modeling and a supervised learning algorithm for context identification.     

Multiresolution FIR neural-network-based learning algorithm applied to network traffic prediction

In this paper, a multiresolution finite-impulse-response (FIR) neural-network-based learning algorithm using the maximal overlap discrete wavelet transform (MODWT) is proposed. The multiresolution learning algorithm employs the analysis framework of wavelet theory, which decomposes a signal into wavelet coefficients and scaling coefficients. The translation-invariant property of the MODWT allows alignment of events in a multiresolution analysis with respect to the original time series and, therefore, preserving the integrity of some transient events. A learning algorithm is also derived for adapting the gain of the activation functions at each level of resolution. The proposed multiresolution FIR neural-network-based learning algorithm is applied to network traffic prediction (real-world aggregate Ethernet traffic data) with comparable results. These results indicate that the generalization ability of the FIR neural network is improved by the proposed multiresolution learning algorithm.     

Evolutionary algorithms for fuzzy control system design

This paper provides an overview on evolutionary learning methods for the automated design and optimization of fuzzy logic controllers. In a genetic tuning process, an evolutionary algorithm adjusts the membership functions or scaling factors of a predefined fuzzy controller based on a performance index that specifies the desired control behavior. Genetic learning processes deal with the automated design of the fuzzy rule base. Their objective is to generate a set of fuzzy if-then rules that establishes the appropriate mapping from input states to control actions. We describe two applications of genetic-fuzzy systems in detail: an evolution strategy that tunes the scaling and membership functions of a fuzzy cart-pole balancing controller and a genetic algorithm that learns the fuzzy control rules for an obstacle-avoidance behavior of a mobile robot     

支持应急通信的认知网络QoS技术

文章提出支持应急通信的认知网络体系结构与模型,以及在此基础上涉及的认知模型服务质量控制和优化策略、智能决策和学习算法,目标在于通过对网络环境状态的观察和学习,智能决策并自适应调整节点行为,进而达到对网络性能的优化。     

Gradient-based learning applied to document recognition

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day