Ah Chung Tsoi

Face recognition: a convolutional neural-network approach

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Locally recurrent globally feedforward networks: a critical review of architectures

In this paper, we will consider a number of local-recurrent-global-feedforward (LRGF) networks that have been introduced by a number of research groups in the past few years. We first analyze the various architectures, with a view to highlighting their differences. Then we introduce a general LRGF network structure that includes most of the network architectures that have been proposed to date. Finally we will indicate some open issues concerning these types of networks.

Learning fuzzy inference systems using an adaptive membership function scheme

An adaptive membership function scheme for general additive fuzzy systems is proposed in this paper. The proposed scheme can adapt a proper membership function for any nonlinear input-output mapping, based upon a minimum number of rules and an initial approximate membership function. This parameter adjustment procedure is performed by computing the error between the actual and the desired decision surface. Using the proposed adaptive scheme for fuzzy system, the number of rules can be minimized. Nonlinear function approximation and truck backer-upper control system are employed to demonstrate the viability of the proposed method.

A new approach to adaptive fuzzy control: the controller output error method

The controller output error method (COEM) is introduced and applied to the design of adaptive fuzzy control systems. The method employs a gradient descent algorithm to minimize a cost function which is based on the error at the controller output. This contrasts with more conventional methods which use the error at the plant output. The cost function is minimized by adapting some or all of the parameters of the fuzzy controller. The proposed adaptive fuzzy controller is applied to the adaptive control of a nonlinear plant and is shown to be capable of providing good overall system performance.

Matrix formulation of fuzzy rule-based systems

In this paper, a matrix formulation of fuzzy rule based systems is introduced. A gradient descent training algorithm for the determination of the unknown parameters can also be expressed in a matrix form for various adaptive fuzzy networks. When converting a rule-based system to the proposed matrix formulation, only three sets of linear/nonlinear equations are required instead of set of rules and an inference mechanism. There are a number of advantages which the matrix formulation has compared with the linguistic approach. Firstly, it obviates the differences among the various architectures; and secondly, it is much easier to organize data in the implementation or simulation of the fuzzy system. The formulation will be illustrated by a number of examples.

Interpretation preservation of adaptive fuzzy inference systems

The membership functions of an adaptive fuzzy inference system, during the adaptation process, may lose the meaning which was initially assigned to them. In this paper, the concept of rough sets is used to propose a constraint training algorithm. The proposed algorithm maintains the interpretation of the adaptive fuzzy inference systems during the training. The constraints on membership functions are implemented by means of hard or soft limit bounds on the updating parameters of membership functions. An example to illustrate the algorithm is included.

Blind deconvolution of signals using a complex recurrent network

An algorithm for the separation of mixtures of signals was derived by Jutten and Herault (1991) under the assumption that the signals are independent. This algorithm is based on higher order moments and has also been applied to deconvolving signal mixtures. In practical problems where the order of the convolving filter may be high, frequency domain approaches are known to provide a more computationally efficient method of deconvolution. In this paper, the authors introduce a complex recurrent network structure for performing blind deconvolution. The aim is to investigate the performance of this approach for separating unknown, convolved signals which may occur in a situation such as the well-known cocktail-party problem.<<ETX>>

A unifying view of some training algorithms for multilayer perceptrons with FIR filter synapses

Concerns neural network architectures for modelling time-dependent signals. A number of algorithms have been published for multilayer perceptrons with synapses described by finite impulse response (FIR) and infinite impulse response (IIR) filters (the latter case is also known as locally recurrent globally feedforward networks). The derivations of these algorithms have used different approaches in calculating the gradients, and in this paper we present a short, but unifying account of how these different algorithms compare for the FIR case, both in derivation, and performance. A new algorithm is subsequently presented. In this paper, results are compared for the Mackey-Glass chaotic time series (1977) against a number of other methods including a standard multilayer perceptron, and a local approximation method.<<ETX>>

Importance of membership functions: a comparative study on different learning methods for fuzzy inference systems

This paper investigates different adaptive structures for fuzzy inference systems. We examine the effect of membership functions on reasoning process when the number of rules is fixed. Three commonly used membership function shapes have been employed in this study. It has been shown that membership functions have the dominant effect on reasoning process rather than number of rules or inference mechanism. We compare our adaptive membership function scheme with two already proposed by others.<<ETX>>

Single net indirect learning architecture

This paper presents a novel indirect learning architecture which uses a single neural network in implementation. The new architecture generates the error signal required in training the controller network by an innovative design using a memory element and few switches. The new controller needs only half the number of neurons and connection weights in comparison with the original indirect learning architecture. Also given are the simulation results in controlling a nonlinear plant.