Planning with a functional neural network architecture

Introduces the concept of planning in an interactive environment between two systems: the challenger and the responder. The responder's task is to produce behavior that relates to the challenger's behavior through some response function. In this setup, we concentrate planning on the responder's actions and use the produced plan in order to control the responder. In general, the responder is assumed to be a nonlinear system whose input-output (I/O) map may be expressed by a Volterra series. The planner uses an estimate of the challenger's future output sequence, the response function, and a model of the responder's I/O relation implemented through a functional artificial neural network (FANN) architecture, in order to produce the input sequence that will be applied to the responder in the future, in parallel-time with the challenger's corresponding output sequence. The responder accepts input from the planner, which may be combined with feedback information, in order to produce an output sequence that relates to the challenger's output sequence according to the response function. The importance of planning for the generation of smooth behavior is discussed, and the effectiveness of the planner's implementation using neural network technology is demonstrated with an example.     

Recognition of coloured and textured images through a multi-scale neural architecture with orientational filtering and chromatic diffusion

The aim of this paper is to outline a multiple scale neural model to recognise colour images of textured scenes. This model combines colour and textural information in order to recognise colour texture images through the operation of two main components: a segmentation component composed of the colour opponent system (COS) and the chromatic segmentation system (CSS); and a recognition component formed by an ARTMAP-based neural network with scale and orientation-invariance properties. Segmentation is achieved by perceptual contour extraction and diffusion processes on the colour opponent channels based on the human psychophysical theory of colour perception. This colour regions enhancement along with their local textural features constitutes the recognition pattern to be sent to the supervised neural classifier. The CSS accomplishes the colour region enhancement through a multiple scale loop of oriented filters and competition–cooperation mechanisms. Afterwards, the neural architecture performs an attentive recognition of the scene using those oriented filters responses and the chromatic diffusions. Some comparative tests with other models are included in order to prove the recognition capabilities of this neural architecture and how the use of colour information encourages the texture classification and the accuracy of the boundary detection.     

Navigating mobile robots with a modular neural architecture

Neural architectures have been proposed to navigate mobile robots within several environment definitions. In this paper a new neural modular constructive approach to navigate mobile robots in unknown environments is presented. The problem, in its basic form, consists of defining and executing a trajectory to a pre-defined goal while avoiding all obstacles, in an unknown environment. Some crucial issues arise when trying to solve this problem, such as an overflow of sensorial information and conflicting objectives. Most neural network (NN) approaches to this problem focus on a monolithic system, i.e., a system with only one neural network that receives and analyses all available information, resulting in conflicting training patterns, long training times and poor generalisation. The work presented in this article circumvents these problems by the use of a constructive modular NN. Navigation capabilities were proven with the NOMAD 200 mobile robot.     

自适应模糊神经网络研究

模糊神经网络提供了从人工神经网络中模糊规则的抽取。本文研究模糊神经网络的自适应学习，规则插入和抽取及神经－模糊推理的FuNN模型，把遗传算法作为系统模糊规则选择的自适应策略之一。     

Scalable communications for a million-core neural processing architecture

The design of a new high-performance computing platform to model biological neural networks requires scalable, layered communications in both hardware and software. SpiNNaker’s hardware is based upon Multi-Processor System-on-Chips (MPSoCs) with flexible, power-efficient, custom communication between processors and chips. The architecture scales from a single 18-processor chip to over 1 million processors and to simulations of billion-neuron, trillion-synapse models, with tens of trillions of neural spike-event packets conveyed each second. The communication networks and overlying protocols are key to the successful operation of the SpiNNaker architecture, designed together to maximise performance and minimise the power demands of the platform. SpiNNaker is a work in progress, having recently reached a major milestone with the delivery of the first MPSoCs. This paper presents the architectural justification, which is now supported by preliminary measured results of silicon performance, indicating that it is indeed scalable to a million-plus processor system.     

Deformation invariant visual object recognition: Experiments with a self-organising neural architecture

A self-organising neural network architecture for grey-scale visual object rcognition is presented. The network is composed of three processing layers with an architecture designed to give deformation tolerance. The processing layers involve feature extraction, sub-pattern detection and classification. Training is generally performed on-line in an unsupervised manner, classes being created when objects are presented that cannot be classified. The results given show the effect of the two discrimination parameters when the network is applied to two very different sets of images, namely hand written numerals and hand gestures images. The sensitivity of the network to the parameters that govern the size of detectable patterns and the areas over which they are detected is also tested. The robustness of the network to the order of image presentation is also demonstrated. The results show that parameter choice is not critical and heuristically chosen parameters provide near optimum performance.     

Convergence properties of eigenvalues of space discretized diffusion equations

A theorem is presented in this paper to establish the convergence of eigenvalues of space discretized Diffusion equation. The computational results confirm this.     

A neural architecture for a class of abduction problems

The general task of abduction is to infer a hypothesis that best explains a set of data. A typical subtask of this is to synthesize a composite hypothesis that best explains the entire data from elementary hypotheses which can explain portions of it. The synthesis subtask of abduction is computationally expensive, more so in the presence of certain types of interactions between the elementary hypotheses. In this paper, we first formulate the abduction task as a nonmonotonic constrained-optimization problem. We then consider a special version of the general abduction task that is linear and monotonic. Next, we describe a neural network based on the Hopfield model of computation for the special version of the abduction task. The connections in this network are symmetric, the energy function contains product forms, and the minimization of this function requires a network of order greater than two. We then discuss another neural architecture which is composed of functional modules that reflect the structure of the abduction task. The connections in this second-order network are asymmetric. We conclude with a discussion of how the second architecture may be extended to address the general abduction task.     

An analog processor architecture for a neural network classifier

Many neural-like algorithms currently under study support classification tasks. Several of these algorithms base their functionality on LVQ-like procedures to find locations of centroids in the data space, and on kernel (or radial-basis) functions centered on these centroids to approximate functions or probability densities. A generic analog chip could implement in a parallel way all basic functions found in these algorithms, permitting construction of a fast, portable classification system     

Predicting sun spots using a layered perceptron neural network

Interest in neural networks has expanded rapidly in recent years. Selecting the best structure for a given task, however, remains a critical issue in neural-network design. Although the performance of a network clearly depends on its structure, the procedure for selecting the optimal structure has not been thoroughly investigated, it is well known that the number of hidden units must be sufficient to discriminate each observation correctly. A large number of hidden units requires extensive computational time for training and often times prediction results may not be as accurate as expected. This study attempts to apply the principal component analysis (PCA) to determine the structure of a multilayered neural network for time series forecasting problems. The main focus is to determine the number of hidden units for a multilayered feedforward network. One empirical experiment with sunspot data is used to demonstrate the usefulness of the proposed approach.     

Evolutionary approximation and neural architecture search

Genetic Programming and Evolvable Machines - Automated neural architecture search (NAS) methods are now employed to routinely deliver high-quality neural network architectures for various...     

L-p Fuzzy ARTMAP neural network architecture

In this paper, an L-p based Fuzzy ARTMAP neural network is presented. The category choice of this network is based on the L-p norm. Geometrical properties of this architecture are presented. Comparisons between this category choice and the category choice of the Fuzzy ARTMAP are illustrated. And simulation results on the databases taken from the UCI repository are performed. It will be shown that using the L-p norm is geometrically more attractive. It will operate directly on the input patterns without the need for doing any preprocessing. It should be noted that the Fuzzy ARTMAP architecture requires two preprocessing steps: normalization and complement coding. Simulation results on different databases show the good generalization performance of the L-p Fuzzy ARTMAP compared to the performance of Fuzzy ARTMAP.     

Optimizing feedforward artificial neural network architecture

Despite the fact that feedforward artificial neural networks (ANNs) have been a hot topic of research for many years there still are certain issues regarding the development of an ANN model, resulting in a lack of absolute guarantee that the model will perform well for the problem at hand. The multitude of different approaches that have been adopted in order to deal with this problem have investigated all aspects of the ANN modelling procedure, from training data collection and pre/post-processing to elaborate training schemes and algorithms. Increased attention is especially directed to proposing a systematic way to establish an appropriate architecture in contrast to the current common practice that calls for a repetitive trial-and-error process, which is time-consuming and produces uncertain results.This paper proposes such a methodology for determining the best architecture and is based on the use of a genetic algorithm (GA) and the development of novel criteria that quantify an ANN's performance (both training and generalization) as well as its complexity. This approach is implemented in software and tested based on experimental data capturing workpiece elastic deflection in turning. The intention is to present simultaneously the approach's theoretical background and its practical application in real-life engineering problems. Results show that the approach performs better than a human expert, at the same time offering many advantages in comparison to similar approaches found in literature.     

Intelligent-memory architecture for artificial neural networks

Execution of artificial neural networks, especially for online pattern recognition, mainly depends on time-efficient execution of weighted sums. A new architecture achieves this goal, with a computation time superior to the time complexity of sequential von Neumann machines. This architecture uses additional logic to extend the functionality of conventional RAM. The authors discuss an implementation of this architecture that uses reconfigurable logic     

An analog systolic neural processing architecture

Developed for the VLSI implementation of neural network models, our novel analog architecture adds flexibility and adaptability by incorporating digital processing capabilities. Its systolic-based architecture avoids static storage of analog values by transferring the activation values through the chip's processing units. This proposed combination of analog and digital technologies produces a densely packed, high-speed, scalable architecture, designed to easily accommodate learning capabilities     

EfficientPose: Efficient human pose estimation with neural architecture search

Computational Visual Media - Human pose estimation from image and video is a key task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into...     

RealNet: a neural network architecture for real-time systems scheduling

Real-time embedded systems are spreading to more and more new fields and their scope and complexity have grown dramatically in the last few years. Nowadays, real-time embedded computers or controllers can be found everywhere, both in very simple devices used in everyday life and in professional environments. Real-time embedded systems have to take into account robustness, safety and timeliness. The most-used schedulability analysis is the worst-case response time proposed by Joseph and Pandya (Comput J 29:390–395,1986). This test provides a bivaluated response (yes/no) indicating whether the processes will meet their corresponding deadlines or not. Nevertheless, sometimes the real-time designer might want to know, more exactly, the probability of the processes meeting their deadlines, in order to assess the risk of a failed scheduling depending on critical requirements of the processes. This paper presents RealNet, a neural network architecture that will generate schedules from timing requirements of a real-time system. The RealNet simulator will provide the designer, after iterating and averaging over some trials, an estimation of the probability that the system will not meet the deadlines. Moreover, the knowledge of the critical processes in these schedules will allow the designer to decide whether changes in the implementation are required.This revised version was published online in November 2004 with a correction to the accepted date.     

Predicting time series using neural networks with wavelet-based denoising layers

To avoid the need to pre-process noisy data, two special denoising layers based on wavelet multiresolution analysis have been integrated into layered neural networks. A gradient-based learning algorithm has been developed that uses the same cost function to set both the neural network weights and the free parameters of the denoising layers. The denoising layers, when integrated into feedforward and recurrent neural networks, were validated on three time series prediction problems: the logistic map, a rubber hardness time series, and annual average sunspot numbers. Use of the denoising layers improved the prediction accuracy in both cases.     

人工神经网络预测并行查询响应时间

针对现有查询响应时间预测统计模型存在准确率无法提高、特征选取单一、动态性差的问题,综合考虑查询计划、查询交互两大因素,提出采用结构简单、易搭建的人工神经网络——全连接神经网络预测并行查询响应时间.采集查询计划与查询交互数据作为输入特征,查询真实的响应时间作为预测标签,训练模型,进行预测.此方法不需要预先知道样本数据的数...