GYAN: A methodology for rule extraction from artificial neural networks

Artificial neural network (ANN) learning methods provide a robust and non-linear approach to approximating the target function for many classification, regression and clustering problems. ANNs have demonstrated good predictive performance in a wide variety of practical problems. However, there are strong arguments as to why ANNs are not sufficient for the general representation of knowledge. The arguments are the poor comprehensibility of the learned ANN, and the inability to represent explanation structures. The overall objective of this thesis is to address these issues by: (1) explanation of the decision process in ANNs in the form of symbolic rules (predicate rules with variables); and (2) provision of explanatory capability by mapping the general conceptual knowledge that is learned by the neural networks into a knowledge base to be used in a rule-based reasoning system. A multi-stage methodology GYAN is developed and evaluated for the task of extracting knowledge from the trained ANNs. The extracted knowledge is represented in the form of restricted first-order logic rules, and subsequently allows user interaction by interfacing with a knowledge based reasoner. The performance of GYAN is demonstrated using a number of real world and artificial data sets. The empirical results demonstrate that: (1) an equivalent symbolic interpretation is derived describing the overall behaviour of the ANN with high accuracy and fidelity, and (2) a concise explanation is given (in terms of rules, facts and predicates activated in a reasoning episode) as to why a particular instance is being classified into a certain category.

The application of neural networks to induction machine control

Neural networks (NNs) are discussed in connection with their possible use in induction machine drives. The mathematical model of the NN as well as a commonly used learning algorithm is presented. Possible applications of NNs to induction machine control are discussed. A simulation of an NN successfully identifying the nonlinear multivariable model of an induction-machine stator transfer function is presented. Previously published applications are discussed, and some possible future applications are proposed.

Identification and control of induction machines using artificial neural networks

The use of artificial neural networks (ANNs) to identify and control induction machines is proposed. Two systems are presented: a system to adaptively control the stator currents via identification of the electrical dynamics, and a system to adaptively control the rotor speed via identification of the mechanical and current-fed system dynamics. Both systems are inherently adaptive as well as self-commissioning. The current controller is a completely general nonlinear controller which can be used together with any drive algorithm. Various advantages of these control schemes over conventional schemes are cited, and the combined speed and current control scheme is compared with the standard vector control scheme

Identification and control of induction machines using artificial neural networks

This paper proposes the use of artificial neural networks (ANNs) to identify and control an induction machine. Two systems are presented: a system to adaptively control the stator currents via identification of the electrical dynamics; and a system to adaptively control the rotor speed via identification of the mechanical and current-fed system dynamics. Various advantages of these control schemes over other conventional schemes are cited and the performance of the combined speed and current control scheme is compared with that of the standard vector control scheme

Alleviating ‘overfitting’ via genetically-regularised neural network

A hybrid genetic algorithm/scaled conjugate gradient regularisation method is designed to alleviate ANN `over-fitting'. In application to day-ahead load forecasting, the proposed algorithm performs better than early-stopping and Bayesian regularisation, showing promising initial results.

The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Neural network learning:theoretical foundations

This important work describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Chapters survey research on pattern classification with binary-output networks, including a discussion of the relevance of the Vapnik Chervonenkis dimension, and of estimates of the dimension for several neural network models. In addition, Anthony and Bartlett develop a model of classification by real-output networks, and demonstrate the usefulness of classification with a "large margin." The authors explain the role of scale-sensitive versions of the Vapnik Chervonenkis dimension in large margin classification, and in real prediction. Key chapters also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient, constructive learning algorithms. The book is self-contained and accessible to researchers and graduate students in computer science, engineering, and mathematics

Aerial image analysis using spiking neural networks with application to power line corridor monitoring

Trees, shrubs and other vegetation are of continued importance to the environment and our daily life. They provide shade around our roads and houses, offer a habitat for birds and wildlife, and absorb air pollutants. However, vegetation touching power lines is a risk to public safety and the environment, and one of the main causes of power supply problems. Vegetation management, which includes tree trimming and vegetation control, is a significant cost component of the maintenance of electrical infrastructure. For example, Ergon Energy, the Australia’s largest geographic footprint energy distributor, currently spends over $80 million a year inspecting and managing vegetation that encroach on power line assets. Currently, most vegetation management programs for distribution systems are calendar-based ground patrol. However, calendar-based inspection by linesman is labour-intensive, time consuming and expensive. It also results in some zones being trimmed more frequently than needed and others not cut often enough. Moreover, it’s seldom practicable to measure all the plants around power line corridors by field methods. Remote sensing data captured from airborne sensors has great potential in assisting vegetation management in power line corridors. This thesis presented a comprehensive study on using spiking neural networks in a specific image analysis application: power line corridor monitoring. Theoretically, the thesis focuses on a biologically inspired spiking cortical model: pulse coupled neural network (PCNN). The original PCNN model was simplified in order to better analyze the pulse dynamics and control the performance. Some new and effective algorithms were developed based on the proposed spiking cortical model for object detection, image segmentation and invariant feature extraction. The developed algorithms were evaluated in a number of experiments using real image data collected from our flight trails. The experimental results demonstrated the effectiveness and advantages of spiking neural networks in image processing tasks. Operationally, the knowledge gained from this research project offers a good reference to our industry partner (i.e. Ergon Energy) and other energy utilities who wants to improve their vegetation management activities. The novel approaches described in this thesis showed the potential of using the cutting edge sensor technologies and intelligent computing techniques in improve power line corridor monitoring. The lessons learnt from this project are also expected to increase the confidence of energy companies to move from traditional vegetation management strategy to a more automated, accurate and cost-effective solution using aerial remote sensing techniques.

Frequency response function based structural damage detection using artificial neural networks

Damage detection in structures has become increasingly important in recent years. While a number of damage detection and localization methods have been proposed, few attempts have been made to explore the structure damage with frequency response functions (FRFs). This paper illustrates the damage identification and condition assessment of a beam structure using a new frequency response functions (FRFs) based damage index and Artificial Neural Networks (ANNs). In practice, usage of all available FRF data as an input to artificial neural networks makes the training and convergence impossible. Therefore one of the data reduction techniques Principal Component Analysis (PCA) is introduced in the algorithm. In the proposed procedure, a large set of FRFs are divided into sub-sets in order to find the damage indices for different frequency points of different damage scenarios. The basic idea of this method is to establish features of damaged structure using FRFs from different measurement points of different sub-sets of intact structure. Then using these features, damage indices of different damage cases of the structure are identified after reconstructing of available FRF data using PCA. The obtained damage indices corresponding to different damage locations and severities are introduced as input variable to developed artificial neural networks. Finally, the effectiveness of the proposed method is illustrated and validated by using the finite element modal of a beam structure. The illustrated results show that the PCA based damage index is suitable and effective for structural damage detection and condition assessment of building structures.