Learning in the multiple class random neural network

Spiked recurrent neural networks with "multiple classes" of signals have been recently introduced by Gelenbe and Fourneau (1999), as an extension of the recurrent spiked random neural network introduced by Gelenbe (1989). These new networks can represent interconnected neurons, which simultaneously process multiple streams of data such as the color information of images, or networks which simultaneously process streams of data from multiple sensors. This paper introduces a learning algorithm which applies both to recurrent and feedforward multiple signal class random neural networks (MCRNNs). It is based on gradient descent optimization of a cost function. The algorithm exploits the analytical properties of the MCRNN and requires the solution of a system of nC linear and nC nonlinear equations (where C is the number of signal classes and n is the number of neurons) each time the network learns a new input-output pair. Thus, the algorithm is of O([nC]/sup 3/) complexity for the recurrent case, and O([nC]/sup 2/) for a feedforward MCRNN. Finally, we apply this learning algorithm to color texture modeling (learning), based on learning the weights of a recurrent network directly from the color texture image. The same trained recurrent network is then used to generate a synthetic texture that imitates the original. This approach is illustrated with various synthetic and natural textures.     

A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation

This work presents a new sequential learning algorithm for radial basis function (RBF) networks referred to as generalized growing and pruning algorithm for RBF (GGAP-RBF). The paper first introduces the concept of significance for the hidden neurons and then uses it in the learning algorithm to realize parsimonious networks. The growing and pruning strategy of GGAP-RBF is based on linking the required learning accuracy with the significance of the nearest or intentionally added new neuron. Significance of a neuron is a measure of the average information content of that neuron. The GGAP-RBF algorithm can be used for any arbitrary sampling density for training samples and is derived from a rigorous statistical point of view. Simulation results for bench mark problems in the function approximation area show that the GGAP-RBF outperforms several other sequential learning algorithms in terms of learning speed, network size and generalization performance regardless of the sampling density function of the training data.     

Multifeedback-Layer Neural Network

The architecture and training procedure of a novel recurrent neural network (RNN), referred to as the multifeedback-layer neural network (MFLNN), is described in this paper. The main difference of the proposed network compared to the available RNNs is that the temporal relations are provided by means of neurons arranged in three feedback layers, not by simple feedback elements, in order to enrich the representation capabilities of the recurrent networks. The feedback layers provide local and global recurrences via nonlinear processing elements. In these feedback layers, weighted sums of the delayed outputs of the hidden and of the output layers are passed through certain activation functions and applied to the feedforward neurons via adjustable weights. Both online and offline training procedures based on the backpropagation through time (BPTT) algorithm are developed. The adjoint model of the MFLNN is built to compute the derivatives with respect to the MFLNN weights which are then used in the training procedures. The Levenberg-Marquardt (LM) method with a trust region approach is used to update the MFLNN weights. The performance of the MFLNN is demonstrated by applying to several illustrative temporal problems including chaotic time series prediction and nonlinear dynamic system identification, and it performed better than several networks available in the literature     

Lattice Dynamical Wavelet Neural Networks Implemented Using Particle Swarm Optimization for Spatio–Temporal System Identification

In this brief, by combining an efficient wavelet representation with a coupled map lattice model, a new family of adaptive wavelet neural networks, called lattice dynamical wavelet neural networks (LDWNNs), is introduced for spatio-temporal system identification. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the OPP algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, however, may be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. An example for a real spatio-temporal system identification problem is presented to demonstrate the performance of the proposed new modeling framework.     

A machine learning method for extracting symbolic knowledge from recurrent neural networks

Neural networks do not readily provide an explanation of the knowledge stored in their weights as part of their information processing. Until recently, neural networks were considered to be black boxes, with the knowledge stored in their weights not readily accessible. Since then, research has resulted in a number of algorithms for extracting knowledge in symbolic form from trained neural networks. This article addresses the extraction of knowledge in symbolic form from recurrent neural networks trained to behave like deterministic finite-state automata (DFAs). To date, methods used to extract knowledge from such networks have relied on the hypothesis that networks' states tend to cluster and that clusters of network states correspond to DFA states. The computational complexity of such a cluster analysis has led to heuristics that either limit the number of clusters that may form during training or limit the exploration of the space of hidden recurrent state neurons. These limitations, while necessary, may lead to decreased fidelity, in which the extracted knowledge may not model the true behavior of a trained network, perhaps not even for the training set. The method proposed here uses a polynomial time, symbolic learning algorithm to infer DFAs solely from the observation of a trained network's input-output behavior. Thus, this method has the potential to increase the fidelity of the extracted knowledge.     

Learning beyond finite memory in recurrent networks of spiking neurons

We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feedforward spiking neuron networks, SpikeProp (Bohte, Kok, & La Poutré, 2002), to recurrent network topologies, so that temporal dependencies in the input stream are taken into account. It is shown that temporal structures with unbounded input memory specified by simple Moore machines (MM) can be induced by recurrent spiking neuron networks (RSNN). The networks are able to discover pulse-coded representations of abstract information processing states coding potentially unbounded histories of processed inputs. We show that it is often possible to extract from trained RSNN the target MM by grouping together similar spike trains appearing in the recurrent layer. Even when the target MM was not perfectly induced in a RSNN, the extraction procedure was able to reveal weaknesses of the induced mechanism and the extent to which the target machine had been learned.     

A multiobjective genetic algorithm for obtaining the optimal size of a recurrent neural network for grammatical inference

Grammatical inference has been extensively studied in recent years as a result of its wide field of application, and in turn, recurrent neural networks have proved themselves to be a good tool for grammatical inference. The learning algorithms for these neural networks, however, have been far less studied than those for feed-forward neural networks. Classical training methods for recurrent neural networks suffer from being trapped in local minimal and having a high computational time. In addition, selecting the optimal size of a neural network for a particular application is a difficult task. This suggests that the problems of developing methods to determine optimal topologies and new training algorithms should be studied.In this paper, we present a multi-objective evolutionary algorithm which is able to determine the optimal size of recurrent neural networks in any particular application. This is specially analyzed in the case of grammatical inference: in particular, we study how to establish the optimal size of a recurrent neural network in order to learn positive and negative examples in a certain language, and how to determine the corresponding automaton using a self-organizing map once the training has been completed.     

一种新的对角回归神经网络快速学习算法

提出一种新的动态对角回归神经网络学习算法－局部动态误差反传算法（LDBP），该算法定义了一种新的局部均方差函数，并为回归单元建立一种新的学习结构。如果估计出各层的期望输出值，多层回归网络便可分解成一组自适应单元（Adaline），而每个单元可通过二次优化方法进行训练。采用可在有限步人找出全局最优解的共轭梯度法（CG）进行寻优。由于学习过程采用超线性搜索，大大减少了循环步数和计算时间。     

Neurocontrol of nonlinear dynamical systems with Kalman filtertrained recurrent networks

Although the potential of the powerful mapping and representational capabilities of recurrent network architectures is generally recognized by the neural network research community, recurrent neural networks have not been widely used for the control of nonlinear dynamical systems, possibly due to the relative ineffectiveness of simple gradient descent training algorithms. Developments in the use of parameter-based extended Kalman filter algorithms for training recurrent networks may provide a mechanism by which these architectures will prove to be of practical value. This paper presents a decoupled extended Kalman filter (DEKF) algorithm for training of recurrent networks with special emphasis on application to control problems. We demonstrate in simulation the application of the DEKF algorithm to a series of example control problems ranging from the well-known cart-pole and bioreactor benchmark problems to an automotive subsystem, engine idle speed control. These simulations suggest that recurrent controller networks trained by Kalman filter methods can combine the traditional features of state-space controllers and observers in a homogeneous architecture for nonlinear dynamical systems, while simultaneously exhibiting less sensitivity than do purely feedforward controller networks to changes in plant parameters and measurement noise.     

递归pi-sigma神经网络的带惩罚项的梯度算法分析

传统的梯度算法存在收敛速度过慢的问题,针对这个问题,提出一种将惩罚项加到传统误差函数的梯度算法以训练递归pi-sigma神经网络,算法不仅提高了神经网络的泛化能力,而且克服了因网络初始权值选取过小而导致的收敛速度过慢的问题,相比不带惩罚项的梯度算法提高了收敛速度。从理论上分析了带惩罚项的梯度算法的收敛性,并通过实验验证了算法的有效性。     

A Hybrid Training Algorithm for Feedforward Neural Networks

Feedforward neural networks (FNN) have been proposed to solve complex problems in pattern recognition, classification and function approximation. Despite the general success of learning methods for FNN, such as the backpropagation (BP) algorithm, second-order algorithms, long learning time for convergence remains a problem to be overcome. In this paper, we propose a new hybrid algorithm for a FNN that combines unsupervised training for the hidden neurons (Kohonen algorithm) and supervised training for the output neurons (gradient descent method). Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.     

An analog VLSI recurrent neural network learning a continuous-timetrajectory

Real-time algorithms for gradient descent supervised learning in recurrent dynamical neural networks fail to support scalable VLSI implementation, due to their complexity which grows sharply with the network dimension. We present an alternative implementation in analog VLSI, which employs a stochastic perturbation algorithm to observe the gradient of the error index directly on the network in random directions of the parameter space, thereby avoiding the tedious task of deriving the gradient from an explicit model of the network dynamics. The network contains six fully recurrent neurons with continuous-time dynamics, providing 42 free parameters which comprise connection strengths and thresholds. The chip implementing the network includes local provisions supporting both the learning and storage of the parameters, integrated in a scalable architecture which can be readily expanded for applications of learning recurrent dynamical networks requiring larger dimensionality. We describe and characterize the functional elements comprising the implemented recurrent network and integrated learning system, and include experimental results obtained from training the network to represent a quadrature-phase oscillator.     

Pruning recurrent neural networks for improved generalizationperformance

Determining the architecture of a neural network is an important issue for any learning task. For recurrent neural networks no general methods exist that permit the estimation of the number of layers of hidden neurons, the size of layers or the number of weights. We present a simple pruning heuristic that significantly improves the generalization performance of trained recurrent networks. We illustrate this heuristic by training a fully recurrent neural network on positive and negative strings of a regular grammar. We also show that rules extracted from networks trained with this pruning heuristic are more consistent with the rules to be learned. This performance improvement is obtained by pruning and retraining the networks. Simulations are shown for training and pruning a recurrent neural net on strings generated by two regular grammars, a randomly-generated 10-state grammar and an 8-state, triple-parity grammar. Further simulations indicate that this pruning method can have generalization performance superior to that obtained by training with weight decay.     

一种新的RBF神经元网络分类算法

为了改善对人工神经网络行为的认识和研究中的"黑匣子"式的难以处理的状态,基于RBF神经元模型的几何解释,提出了一种新的RBF神经网络分类算法,算法把RBF神经元看作是高维空间里的超球面,从而将神经网络训练问题转化为点集"包含"问题.同传统的RBF网络相比,算法能够自动地优化RBF网络中核函数的个数、中心和宽度,同时,省去了传统RBF神经网络输出层线性连接权的计算,简化了网络的学习过程,大大缩短了训练时间,并且通过实验证明了算法的有效性.     

The performance evaluation of diagonal recurrent neural network with different chaos neurons

In this paper, different chaos neurons are added in hidden layer of diagonal recurrent neural network. The advanced networks can solve the problem of long training time because of the convergence of chaos neuron. The Logistic map, the Chebyshev map, and the Sine map are used to construct networks. These networks are applied for image compression in order to compare their performance. The result of simulation test shows that the networks with chaos neurons are superior to traditional diagonal recurrent network in the effect of image reconstruction, and the networks with different chaotic maps are analyzed and compared for the first time.

     

递归神经网络的设计与应用

结合实例,给出了递归神经网络的完整设计步骤,包括网络结构的选定,学习算法的选择和网络参数的训练过程。重点研究了学习速率的初始值选取及其调整顺序。给出的递归网络的设计方法,可以适用于多种递归神经网络。     

基于反馈神经网络的动态化工过程建模

针对非线性动态化工过程建模存在的问题,提出了一种新的反馈神经网络结构,并将状态反馈、时间序列延尺以及集中节点的概念结合起来,用于提高反馈神经网络的性能,同时又使得网络结构不至于太复杂,在用此网络结构建模的时间,成功地将BP算法用一网络模型的训练。文中将这种反馈神经网络结构分别对一个单输入单输出（SISO）的非线笥动态系统和一个多输入单输出（SIMO）的连续全混釜（CSTR）模型进行建模,并将所得模型与基于表态BP神经神经所得的模型在模型输出精度和抗干扰性等方面进行了比较,证明了该反馈神经在动态过程建模中能够比静态BP模型更好地反映出动态过程的输入输出关系,并具有一定的抗干扰能力。     

一种估计前馈神经网络中隐层神经元数目的新方法

前馈神经网络中隐层神经元的数目一般凭经验的给出，这种方法往往造成隐单元数目的不足或过甚，从而导致网络存储容量不够或出现学习过拟现象，本研究提出了一种基于信息熵的估计三层前馈神经网络隐结点数目的方法，该方法首先利用训练集来训练具有足够隐单元数目的初始神经网络，然后计算训练集中能被训练过的神经网络正确识别的样本在隐层神经元的激活值，并对其进行排序，计算这些激活值的各种划分的信息增益，从而构造能将整个样本空间正确划分的决策树，最后遍历整棵树寻找重要的相关隐层神经元，并删除冗余无关的其它隐单元，从而估计神经网络中隐层神经元的较佳数目，文章最后以构造用于茶叶品质评定的具有较佳隐单元数目的神经网络为例，介绍本方法的使用，结果表明，本方法能有效估计前馈神经网络的隐单元数目。     

Training recurrent neural networks using a hybrid algorithm

This paper proposes a new hybrid approach for recurrent neural networks (RNN). The basic idea of this approach is to train an input layer by unsupervised learning and an output layer by supervised learning. In this method, the Kohonen algorithm is used for unsupervised learning, and dynamic gradient descent method is used for supervised learning. The performances of the proposed algorithm are compared with backpropagation through time (BPTT) on three benchmark problems. Simulation results show that the performances of the new proposed algorithm exceed the standard backpropagation through time in the reduction of the total number of iterations and in the learning time required in the training process.     

On the improvement of the real time recurrent learning algorithm for recurrent neural networks

This paper reviews different approaches to improving the real time recurrent learning (RTRL) algorithm and attempts to group them into common frameworks. The characteristics of sub-grouping strategy, mode exchange RTRL, and cellular genetic algorithms are discussed. The relationships between these algorithms are highlighted and their time complexities and convergence capability are compared. The learning algorithms are applied to train recurrent neural networks in an attempt to solve a long-term dependency problem, to model the Hénon map, and to predict the chaotic intensity pulsations of an NH₃ laser. The results show that the original RTRL algorithm achieves the lowest error among the gradient-based algorithms, but it requires the longest training time; whereas the sub-grouping strategy uses the shortest training time but its convergence capability is the poorest. The results also demonstrate that the cellular genetic algorithm is an alternative means of training recurrent neural networks when the gradient-based methods fail to find an acceptable solution.