MIPAS: A neural network-based multimedia information processing and analysis system

This paper presents the structure and design criteria of a neural network-based multimedia information processing and analysis system (MIPAS) which can be used to deal with more-complicated intelligence issues. According to the structure and design criteria, a software environment (SEMIPAS), which supports the implementation of multimedia information (image + speech, image + characters, speech + characters, image + speech + characters) processing and analysis applications, is implemented and introduced. Under this software environment, a multimedia information processing and analysis system called “To Know the World” is constructed. Experiments show that the multimedia information processing and analysis is much more powerful and effective than single-medium information processing and analysis.     

A neural architecture for visual information processing

We report on the work done at the Institut für Neuroinformatik in Bochum concerning the development of a neural architecture for the information processing of autonomous visually guided systems acting in a natural environment. Since biological systems like our brain are superior to artificial systems in solving such a task, we use findings from neurophysiology and -anatomy as well as psychophysics for defining processing principles and modules that have been implemented on our mobile platform MARVIN. MARVIN is equipped with an active stereo camera system. Our final objective is to define a neural instruction set for early information processing in the sense of a perception for action approach. From the biological paradigm we use principles like active vision, foveation, two-dimensional cortical layers, mapping, and discrete parametric representations in a task-oriented way to solve problems like obstacle avoidance, path planning, scene recognition, tracking, and 3D perception. This paper has the character of an overview of the work done in this field at our institute. Most of the modules presented here were published either in conference proceedings or in journals which will be referenced for a more thorough discussion of each issue.     

用于信息处理的延时混沌神经网络

为了提高混沌神经网络用于信息处理的能力,采用一种参数调节控制方法,通过对一种延时对称全局耦合混沌神经网络的黏合参数的控制研究了网络的动态联想记忆,使被控网络在仅有部分神经元进入周期态的情况下达到输出稳定,并且稳定输出序列只包含与输入模式相关的存储模式及其相反模式。仿真实验说明网络具有良好的容错能力和很高的回忆正确率,适合应用于信息处理和模式识别。     

Dynamical consequences of fast-rising, slow-decaying synapses in neuronal networks

Synapses that rise quickly but have long persistence are shown to have certain computational advantages. They have some unique mathematical properties as well and in some instances can make neurons behave as if they are weakly coupled oscillators. This property allows us to determine their synchronization properties. Furthermore, slowly decaying synapses allow recurrent networks to maintain excitation in the absence of inputs, whereas faster decaying synapses do not. There is an interaction between the synaptic strength and the persistence that allows recurrent networks to fire at low rates if the synapses are sufficiently slow. Waves and localized structures are constructed in spatially extended networks with slowly decaying synapses.     

神经信息实时处理平台的快速开发

针对神经信息处理过程中的高速实时、快速开发、多功能复杂算法实现等需求,对当前几种主流的硬件实时处理开发平台进行比较,并综述神经信息实时处理开发过程及知识产权(IP)核的快速开发方法.同时,对基于可编程片上系统的神经信息实时处理平台快速开发的需求从多平台连接、开发工具之间高效转换和标准化信息处理库三个方面进一步阐述,为神经信息实时处理快速开发的研究提供了参考.     

过程神经元网络及其在时变信息处理中的应用

针对时变信息处理和动态系统建模等类问题,建立了输入输出均为时变函数的过程神经元网络和有理式过程神经元网络2种网络模型.在输入输出为时变函数的过程神经元网络中,过程神经元的时间累积算子取为对时间的积分或其他代数运算,它的时空聚合机制和激励能同时反映外部时变输入信号对输出结果的空间聚合作用和时间累积效应,可实现非线性系统输入、输出之间的复杂映射关系.在有理式过程神经元网络中,其基本信息处理单元为由2个成对偶出现的过程神经元组成,逻辑上分为分子和分母2部分,通过有理式整合后输出,可有效提高过程神经元网络对带有奇异值过程函数的柔韧逼近性和在奇异值点附近反应的灵敏性.分析了2种过程神经元网络模型的性质,给出了具体学习算法,并以油田开发过程模拟和旋转机械故障诊断问题为例,验证了这2种网络模型在时变信息处理中的有效性.     

The evidence for neural information processing with precise spike-times: A survey

This paper surveys recent findings in neuroscience regarding the behavioral relevancy of the precise timing with which real spiking neurons emit spikes. The literature suggests that in almost any system where the processing-speed of a neural (sub)-system is required to be high, the timing of single spikes can be very precise and reliable. Additionally, new, more refined methods are finding precisely timed spikes where previously none where found. This line of evidence thus provides additional motivation for researching the computational properties of networks of artificial spiking neurons that compute with more precisely timed spikes. This revised version was published online in June 2006 with corrections to the Cover Date.     

Effects of multiplicative power law neural noise in visual information processing

The human visual system is intrinsically noisy. The benefits of internal noise as part of visual code are controversial. Here the information-theoretic properties of multiplicative (i.e. signal-dependent) neural noise are investigated. A quasi-linear communication channel model is presented. The model shows that multiplicative power law neural noise promotes the minimum information transfer after efficient coding. It is demonstrated that Weber's law and the human contrast sensitivity function arise on the basis of minimum transfer of information and power law neural noise. The implications of minimum information transfer in self-organized neural networks and weakly coupled neurons are discussed.     

A GCM neural network using cubic logistic map for information processing

A new chaotic neural network described by a modified globally coupled map (GCM) model with cubic logistic map is proposed, which is called CL-GCM model. Its rich dynamical behaviors over a wide range of parameters and the dynamics mechanism of neurons are demonstrated in detail. Furthermore, the network with delay coupling can be precisely controlled to any specified-periodic orbit by feedback control or modulated parameter control with variable threshold. The results of simulations and experiments suggest that the network is controlled successfully. The controlled CL-GCM model exhibits excellent associative memory performance which appears it can output unique fixed pattern or periodic patterns with specified period which contain the stored pattern closest to the initial pattern.

     

Optimizing algebraic and neural methods for information processing in distributed fiber-optical measuring systems

The paper discusses tomography reconstruction of distributed physical fields by means of fiber optical measuring systems (FOMN) [1] for parallel setup of measuring lines with a small number of scanning directions. The approach whose novelty involves measuring network geometry optimization for further application of neural or algebraic technologies to restore a full image of the functions studied is presented. An alternative to choose and apply an appropriate neural network from the set of several, previously trained neural networks of radial-basic type is investigated [2].     

Parallel processing, neural networks and genetic algorithms

In an earlier paper[1] some recent developments in computational technology to structural engineering were described. The developments included: parallel and distributed computing; neural networks; and genetic algorithms. In this paper, the authors concentrate on parallel implementations of neural networks and genetic algorithms. In the final section of the paper the authors show how a parallel finite element analysis may be undertaken in an efficient manner by preprocessing of the finite element model using a genetic algorithm utilizing a neural network predictor. This preprocessing is the partitioning of the finite element mesh into sub-domains to ensure load balancing and minimum interprocessor communication during the parallel finite element analysis on a MIMD distributed memory computer. © 1998 Published by Elsevier Science Limited. All rights reserved.     

Agents for information retrieval: Issues of mobility and coordination

This paper focuses on agent-based applications for information retrieval on the Web, by specifically analysing mobility and coordination issues. On the one hand, mobile agents well suit the requirements of information retrieval in the new dynamic scenario derived from the Internet. This is due to their capability of moving to the place where the information is stored – therefore saving bandwidth – and to their robustness in the presence of unreliable connections. On the other hand, the search for information by several mobile active agents calls for suitable models to rule the interactions among agents and between agents and execution environments. The paper surveys different coordination approaches and evaluates their impact in information retrieval applications based on mobile agents. The survey outlines the advantages of uncoupled coordination models and points out the suitability of a coordination model based on reactive and programmable tuple spaces: they may increase the safety and the security of the environment while simplifying the task of programming distributed mobile agent applications.     

Dynamical sources in information theory: Fundamental intervals and word prefixes

A quite general model of source that comes from dynamical systems theory is introduced. Within this model, some basic problems of algorithmic information theory contexts are analysed. The main tool is a new object, the generalized Ruelle operator, which can be viewed as a “generating” operator for fundamental intervals (associated to information sharing common prefixes). Its dominant spectral objects are linked with important parameters of the source, such as the entropy, and play a central rôle in all the results.     

Knowledge information processing language: ShapeUp

A new logic programming language, ShapeUp, is developed. ShapeUp is an expanded Prolog system with string matching facilities. The language has been developed to give programmers a new computer programming environment, especially for knowledge information processing. This area includes natural language comprehension and intelligent text processing systems with better man-machine interfaces. For this kind of application, character string data play a principal part rather than conventional numerical data. In ShapeUp, string patterns are introduced as Prolog ‘terms’. Their matching process is performed inside the unification. Thus, a program is far simpler and easier to write and read in ShapeUp, than in conventional Prolog systems, and program size is extremely reduced.     

Class 1 neural excitability, conventional synapses, weaklyconnected networks, and mathematical foundations of pulse-coupled models

Many scientists believe that all pulse-coupled neural networks are toy models that are far away from the biological reality. We show, however, that a huge class of biophysically detailed and biologically plausible neural-network models can be transformed into a canonical pulse-coupled form by a piece-wise continuous, possibly noninvertible, change of variables. Such transformations exist when a network satisfies a number of conditions; e,g., it is weakly connected; the neurons are Class 1 excitable (i.e., they can generate action potentials with an arbitrary small frequency); and the synapses between neurons are conventional (i.e., axo-dendritic and axe-somatic). Thus, the difference between studying the pulse-coupled model and Hodgkin-Huxley-type neural networks is just a matter of a coordinate change. Therefore, any piece of information about the pulse-coupled model is valuable since it tells something about all weakly connected networks of Class 1 neurons. For example, we show that the pulse-coupled network of identical neurons does not synchronize in-phase. This confirms Ermentrout's (1996) result that weakly connected Class 1 neurons are difficult to synchronize, regardless of the equations that describe dynamics of each cell.