This paper discusses Memory Neuron Networks as models for identification and adaptive control of nonlinear dynamical systems. These are a class of recurrent networks obtained by adding trainable temporal elements to f...
详细信息
This paper discusses Memory Neuron Networks as models for identification and adaptive control of nonlinear dynamical systems. These are a class of recurrent networks obtained by adding trainable temporal elements to feed-forward networks that makes the output history-sensitive. By virtue of this capability, these networks can identify dynamical systems without having to be explicitly fed with past inputs and outputs. Thus, they can identify systems whose order is unknown or systems with unknown delay. It is argued that for satisfactory modeling of dynamical systems, neural networks should be endowed with such internal memory. The paper presents a preliminary analysis of the learning algorithm, providing theoretical justification for the identification method. Methods for adaptive control of nonlinear systems using these networks are presented. Through extensive simulations, these models are shown to be effective both for identification and model reference adaptive control of nonlinear systems.
In this paper, a simple learning method and a dynamic threshold concept for associative memories (AMs) is presented. The learning approach is designed to store all training patterns with basins of attraction as large ...
详细信息
In this paper, a simple learning method and a dynamic threshold concept for associative memories (AMs) is presented. The learning approach is designed to store all training patterns with basins of attraction as large as possible. After the learning process stops, the dynamic threshold introduces a threshold in the recall phase. It can reduce the probability of converging to spurious states. A large number of computer simulations are implemented to show the improved recalls.
The finite element neural network (FENN)was applied to a non-invasive technique to monitor the plant water status of greenhouse-grown chrysanthemums. The governing differential equation (Poisson's equation) was ut...
详细信息
The finite element neural network (FENN)was applied to a non-invasive technique to monitor the plant water status of greenhouse-grown chrysanthemums. The governing differential equation (Poisson's equation) was utilized for neural information processing. The solution of the Poisson's equation was obtained using the finite element technique. A Kalman filter was used as a learning algorithm of the FENN. It was demonstrated as a practical example of the FENN applications that the FENN provided a means of estimating the leaf water potentials (correlated outputs of the FENN) of a greenhouse-grown chrysanthemum from the digital image data of its leaf (correlated inputs of the FENN) .
This paper discusses learning algorithms of layered neural networks from the standpoint of maximum likelihood estimation. At first we discuss learning algorithms for the most simple network with only one neuron. It is...
详细信息
This paper discusses learning algorithms of layered neural networks from the standpoint of maximum likelihood estimation. At first we discuss learning algorithms for the most simple network with only one neuron. It is shown that Fisher information of the network, namely minus expected values of Hessian matrix, is given by a weighted covariance matrix of input vectors. A learning algorithm is presented on the basis of Fisher's scoring method which makes use of Fisher information instead of Hessian matrix in Newton's method. The algorithm can be interpreted as iterations of weighted least squares method. Then these results are extended to the layered network with one hidden layer. Fisher information for the layered network is given by a weighted covariance matrix of inputs of the network and outputs of hidden units. Since Newton's method for maximization problems has the difficulty when minus Hessian matrix is not positive definite, we propose a learning algorithm which makes use of Fisher information matrix, which is non-negative, instead of Hessian matrix. Moreover, to reduce the computation of full Fisher information matrix, we propose another algorithm which uses only block diagonal elements of Fisher information. The algorithm is reduced to an iterative weighted least squares algorithm in which each unit estimates its own weights by a weighted least squares method. It is experimentally shown that the proposed algorithms converge with fewer iterations than error back-propagation (BP) algorithm.
A new regularization cost function for generalization in real-valued function learning is proposed. This cost function is derived from the maximum likelihood method using a modified sample distribution, and consists o...
详细信息
A new regularization cost function for generalization in real-valued function learning is proposed. This cost function is derived from the maximum likelihood method using a modified sample distribution, and consists of a sum of square errors and a stabilizer which is a function of integrated square derivatives. Each of the regularization parameters which gives the minimum estimation error can be obtained uniquely and non-empirically. The parameters are not constants and change in value during learning. Numerical simulation shows that this cost function predicts the true error accurately and is effective in neural network learning.
Analysis of satellite images requires classification of image objects. Since different categories may have almost the same brightness or feature in high dimensional remote sensing data, many object categories overlap ...
详细信息
Analysis of satellite images requires classification of image objects. Since different categories may have almost the same brightness or feature in high dimensional remote sensing data, many object categories overlap with each other. How to segment the object categories accurately is still an open question. It is widely recognized that the assumptions required by many classification methods (maximum likelihood estimation, etc.) are suspect for textural features based on image pixel brightness. We propose an image feature based neural network approach for the segmentation of AVHRR images. The learning algorithm is a modified backpropagation with gain and weight decay, since feedforward networks using the backpropagation algorithm have been generally successful and enjoy wide popularity. Destructive algorithms that adapt the neural architecture during the training have been developed. The classification accuracy of 100% is reached for a validation data set. Classification result is compared with that of Kohonen's LVQ and basic backpropagation algorithm based pixel-by-pixel method. Visual investigation of the result images shows that our method can not only distinguish the categories with similar signatures very well, but also is robustic to noise.
Neural network which is formed by extensive interconnections of neurons performing simple functions, is a complicated nonlinear dynamic system. By now the stability of neural network systems has only been analysed on ...
详细信息
ISBN:
(纸本)0780314212
Neural network which is formed by extensive interconnections of neurons performing simple functions, is a complicated nonlinear dynamic system. By now the stability of neural network systems has only been analysed on those with restricted connection forms such as symmetrical feedback and feedforward networks, with their sufficient conditions of stability given. Based upon nonlinear system theory, this paper studies neural network system with general connective forms, giving the sufficient conditions of globally asymptotic stability of network. The locally asymptotic stability of the equilibration solutions of multistable-state is also discussed.
In this thesis, the collapse mode of failure of tapered steel beams is examined for three different loading cases. Firstly, for the case when the beam is loaded inside the tip; secondly, when the beam is loaded outsid...
详细信息
In this thesis, the collapse mode of failure of tapered steel beams is examined for three different loading cases. Firstly, for the case when the beam is loaded inside the tip; secondly, when the beam is loaded outside the tip, and thirdly, when the beam is loaded at the tip. The theoretical collapse mode of failure presented here provides an identical collapse load whether obtained from lower or upper bound solutions. Fourteen tests on tapered steel beam specimen were carried out to examine the collapse modes of failure and their ultimate strengths for steel tapered beams loaded inside, outside and at the tip. The experimental collapse loads and their collapse modes of failure are compared with theoretically predicted collapse loads and the proposed collapse mechanisms respectively.
The first elastic yield load of the tapered web panels is assessed on the basis of 'circular Arc Theory' simplified by Davies et al. (6) and is compared with the predicted theoretical collapse loads.
Conclusions are drawn relating to the plastic collapse modes of failure and ultimate strengths of tapered steel beam.
A neuro fuzzy position controller for a servomotor, which is a nonlinear controller and gives much higher control performance for highly nonlinear systems than a linear controller, is proposed. The simulation results ...
详细信息
ISBN:
(纸本)1565550072
A neuro fuzzy position controller for a servomotor, which is a nonlinear controller and gives much higher control performance for highly nonlinear systems than a linear controller, is proposed. The simulation results show that it is robust and has self-tuning capabilities.
暂无评论