Intelligent decision systems have the potential to support and greatly amplify human decision-making across a number of industries and domains. However, despite the rapid improvement in the underlying capabilities of these “intelligent” systems, increasing their acceptance as decision aids in industry has remained a formidable challenge. If intelligent systems are to be successful, and their full impact on decision-making performance realized, a greater understanding of the factors that influence recommendation acceptance from intelligent machines is needed. Through an empirical experiment in the financial services industry, this study investigated the effects of perceived behavioral similarity (similarity state) on the dependent variables of recommendation acceptance, decision performance and decision efficiency under varying conditions of uncertainty (volatility state). It is hypothesized in this study that behavioral similarity as a design element will positively influence the acceptance rate of machine recommendations by human users. The level of uncertainty in the decision context is expected to moderate this relationship. In addition, an increase in recommendation acceptance should positively influence both decision performance and decision efficiency. The quantitative exploration of behavioral similarity as a design element revealed a number of key findings. Most importantly, behavioral similarity was found to positively influence the acceptance rate of machine recommendations. However, uncertainty did not moderate the level of recommendation acceptance as expected. The experiment also revealed that behavioral similarity positively influenced decision performance during periods of elevated uncertainty. This relationship was moderated based on the level of uncertainty in the decision context. The investigation of decision efficiency also revealed a statistically significant result. However, the results for decision efficiency were in the opposite direction of the hypothesized relationship. Interestingly, decisions made with the behaviorally similar decision aid were less efficient, based on length of time to make a decision, compared to decisions made with the low-similarity decision aid. The results of decision efficiency were stable across both levels of uncertainty in the decision context.

The research presented in this thesis is concerned with optimising the structure of Artificial Neural Networks. These techniques are based on computer modelling of biological evolution or foetal development. They are known as Evolutionary, Genetic or Embryological methods. Specifically, Embryological techniques are used to grow Artificial Neural Network topologies. The Embryological Algorithm is an alternative to the popular Genetic Algorithm, which is widely used to achieve similar results. The algorithm grows in the sense that the network structure is added to incrementally and thus changes from a simple form to a more complex form. This is unlike the Genetic Algorithm, which causes the structure of the network to evolve in an unstructured or random way. The thesis outlines the following original work: The operation of the Embryological Algorithm is described and compared with the Genetic Algorithm. The results of an exhaustive literature search in the subject area are reported. The growth strategies which may be used to evolve Artificial Neural Network structure are listed. These growth strategies are integrated into an algorithm for network growth. Experimental results obtained from using such a system are described and there is a discussion of the applications of the approach. Consideration is given of the advantages and disadvantages of this technique and suggestions are made for future work in the area. A new learning algorithm based on Taguchi methods is also described. The report concludes that the method of incremental growth is a useful and powerful technique for defining neural network structures and is more efficient than its alternatives. Recommendations are also made with regard to the types of network to which this approach is best suited. Finally, the report contains a discussion of two important aspects of Genetic or Evolutionary techniques related to the above. These are Modular networks (and their synthesis) and the functionality of the network itself.

This thesis describes a novel approach to the evolution of Modular Artificial Neural Networks. Standard Evolutionary Algorithms, used in this application include: Genetic Algorithms, Evolutionary Strategies, Evolutionary Programming and Genetic Programming; however, these often fail in the evolution of complex systems, particularly when such systems involve multi-domain sensory information which interacts in complex ways with system outputs. The aim in this work is to produce an evolutionary method that allows the structure of the network to evolve from simple to complex as it interacts with a dynamic environment. This new algorithm is therefore based on Incremental Evolution. A simulated model of a legged robot was used as a test-bed for the approach. The algorithm starts with a simple robotic body plan. This then grows incrementally in complexity along with its controlling neural network and the environment it reacts with. The network grows by adding modules to its structure - so the technique may also be termed a Growth Algorithm. Experiments are presented showing the successful evolution of multi-legged gaits and a simple vision system. These are then integrated together to form a complete robotic system. The possibility of the evolution of complex systems is one advantage of the algorithm and it is argued that it represents a possible path towards more advanced artificial intelligence. Applications in Electronics, Computer Science, Mechanical Engineering and Aerospace are also discussed.

The research presented in this thesis examines the area of control systems for robots or animats (animal-like robots). Existing systems have problems in that they require a great deal of manual design or are limited to performing jobs of a single type. For these reasons, a better solution is desired. The system studied here is an Artificial Nervous System (ANS) which is biologically inspired; it is arranged as a hierarchy of layers containing modules operating in parallel. The ANS model has been developed to be flexible, scalable, extensible and modular. The ANS can be implemented using any suitable technology, for many different environments. The implementation focused on the two lowest layers (the reflex and action layers) of the ANS, which are concerned with control and rhythmic movement. Both layers were realised as Artificial Neural Networks (ANN) which were created using Evolutionary Algorithms (EAs). The task of the reflex layer was to control the position of an actuator (such as linear actuators or D.C. motors). The action layer performed the task of Central Pattern Generators (CPG), which produce rhythmic patterns of activity. In particular, different biped and quadruped gait patterns were created. An original neural model was specifically developed for assisting in the creation of these time-based patterns. It is shown in the thesis that Artificial Reflexes and CPGs can be configured successfully using this technique. The Artificial Reflexes were better at generalising across different actuators, without changes, than traditional controllers. Gaits such as pace, trot, gallop and pronk were successfully created using the CPGs. Experiments were conducted to determine whether modularity in the networks had an impact. It has been demonstrated that the degree of modularization in the network influences its evolvability, with more modular networks evolving more efficiently.

The marketing literature so far only considers attraction models with strict functional forms. Greater exibility can be achieved by the neural net based approach introduced which assesses brands' attraction values by means of a perceptron with one hidden layer. Using log-ratio transformed market shares as dependent variables stochastic gradient descent followed by a quasi-Newton method estimates parameters. For store-level data the neural net model performs better and implies a price response qualitatively different from the well-known MNL attraction model. Price elasticities of these competing models also lead to specific managerial implications. (author's abstract) / Series: Working Papers SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Microwave detection techniques based on the theory of perturbation of cavity resonators are commonly used to measure the permittivity and permeability of objects of dielectric and ferrite materials at microwave frequencies. When a small object is introduced into a microwave cavity resonator, the resonant frequency is perturbed. Since it is possible to measure the change in frequency with high accuracy, this provides a valuable method for measuring the electric and magnetic properties of the object. Likewise, these microwave resonators can be used as sensors for sorting dielectric objects. Techniques based upon this principle are in common use for measuring the dielectric and magnetic properties of materials at microwave frequencies for variety of applications. This thesis presents an approach of using Artificial Neural Networks to detect material change in a rectangular cavity. The method is based on the theory of the perturbation of cavity resonators where a change in the resonant frequencies of the cavity is directly proportional to the dielectric constant of the inserted objects. A rectangular cavity test fixture was built and excited with a monopole antenna. The cavity was filled with different materials, and the reflection coefficient of each material was measured over a wide range of frequencies. An intelligent systems approach using an artificial neural network (ANN) methodology was implemented for the automatic material change detection. To develop an automatic detection model, a multi-layer perceptron (MLP) was designed with one hidden layer and gradient descent back-propagation (BP) learning algorithm was used for the ANN training. The network training process was performed in an off-line mode, and after the training process was accomplished, the model was able to learn the rules without knowing any algorithm for automatic detection.

The statistical properties of training, validation and test data play an important role in assuring optimal performance in artificial neural networks (ANN). Re-searchers have proposed randomized data partitioning (RDP) and stratified data partitioning (SDP) methods for partition of input data into training, vali-dation and test datasets. RDP methods based on genetic algorithm (GA) are computationally expensive as the random search space can be in the power of twenty or more for an average sized dataset. For SDP methods, clustering al-gorithms such as self organizing map (SOM) and fuzzy clustering (FC) are used to form strata. It is assumed that data points in any individual stratum are in close statistical agreement. Reported clustering algorithms are designed to form natural clusters. In the case of large multivariate datasets, some of these natural clusters can be big enough such that the furthest data vectors are statis-tically far away from the mean. Further, these algorithms are computationally expensive as well. Here a custom design clustering algorithm (CDCA) has been proposed to overcome these shortcomings. Comparisons have been made using three benchmark case studies, one each from classification, function ap-proximation and prediction domain respectively. The proposed CDCA data partitioning method was evaluated in comparison with SOM, FC and GA based data partitioning methods. It was found that the CDCA data partitioning method not only performed well but also reduced the average CPU time. / Engineering Management

Footings are often founded on multi-layered soil profiles. Real soil profiles are often multi-layered with material constantly varying with depth, which affects the footing response significantly. Furthermore, the properties of the soil are known to vary with location. The spatial variability of soil can be described by random field theory and geostatistics. The research presented in this thesis focuses on quantifying the effect of soil variability on the bearing capacity of rough strip footings on single and two layered, purely-cohesive, spatially variable soil profiles. This has been achieved by using Monte Carlo analysis, where the rough strip footings are founded on simulated soil profiles are analysed using finite element limit analysis. The simulations of virtual soil profiles are carried out using Local Average Subdivision (LAS), a numerical model based on the random field theory. An extensive parametric study has been carried out and the results of the analyses are presented as normalized means and coefficients of variation of bearing capacity factor, and comparisons between different cases are presented. The results indicate that, in general, the mean of the bearing capacity reduces as soil variability increases and the worst case scenario occurs when the correlation length is in the range of 0.5 to 1.0 times the footing width. The problem of estimating the bearing capacity of shallow strip footings founded on multi-layered soil profiles is very complex, due to the incomplete knowledge of interactions and relationships between parameters. Much research has been carried out on single- and two-layered homogeneous soil profiles. At present, the inaccurate weighted average method is the only technique available for estimating the bearing capacity of footing on soils with three or more layers. In this research, artificial neural networks (ANNs) are used to develop meta-models for bearing capacity estimation. ANNs are numerical modelling techniques that imitate the human brain capability to learn from experience. This research is limited to shallow strip footing founded on soil mass consisting of ten layers, which are weightless, purely cohesive and cohesive-frictional. A large number of data has been obtained by using finite element limit analysis. These data are used to train and verify the ANN models. The shear strength (cohesion and friction angle), soil thickness, and footing width are used as model inputs, as they are influencing factors of bearing capacity of footings. The model outputs are the bearing capacities of the footings. The developed ANN-based models are then compared with the weighted average method. Hand-calculation design formulae for estimation of bearing capacity of footings on ten-layered soil profiles, based on the ANN models, are presented. It is shown that the ANN-based models have the ability to predict the bearing capacity of footings on ten-layered soil profiles with a high degree of accuracy, and outperform traditional methods. / http://proxy.library.adelaide.edu.au/login?url= http://library.adelaide.edu.au/cgi-bin/Pwebrecon.cgi?BBID=1368281 / Thesis (Ph.D.) - University of Adelaide, School of Civil, Environmental and Mining Engineering, 2009

Artificial neural networks (ANNs) are essentially a 'black box' technology. The lack of an explanation component prevents the full and complete exploitation of this form of machine learning. During the mid 1990's the field of 'rule extraction' emerged. Rule extraction techniques attempt to derive a human comprehensible explanation structure from a trained ANN. Andrews et.al. (1995) proposed the following reasons for extending the ANN paradigm to include a rule extraction facility: * provision of a user explanation capability * extension of the ANN paradigm to 'safety critical' problem domains * software verification and debugging of ANN components in software systems * improving the generalization of ANN solutions * data exploration and induction of scientific theories * knowledge acquisition for symbolic AI systems An allied area of research is that of 'rule refinement'. In rule refinement an initial rule base, (i.e. what may be termed `prior knowledge') is inserted into an ANN by prestructuring some or all of the network architecture, weights, activation functions, learning rates, etc. The rule refinement process then proceeds in the same way as normal rule extraction viz (1) train the network on the available data set(s); and (2) extract the `refined' rules. Very few ANN techniques have the capability to act as a true rule refinement system. Existing techniques, such as KBANN, (Towell & Shavlik, (1993), are limited in that the rule base used to initialize the network must be a nearly complete, and the refinement process is limited to modifying antecedents. The limitations of existing techniques severely limit their applicability to real world problem domains. Ideally, a rule refinement technique should be able to deal with incomplete initial rule bases, modify antecedents, remove inaccurate rules, and add new knowledge by generating new rules. The motivation for this research project was to develop such a rule refinement system and to investigate its efficacy when applied to both nearly complete and incomplete problem domains. The premise behind rule refinement is that the refined rules better represent the actual domain theory than the initial domain theory used to initialize the network. The hypotheses tested in this research include: * that the utilization of prior domain knowledge will speed up network training, * produce smaller trained networks, * produce more accurate trained networks, and * bias the learning phase towards a solution that 'makes sense' in the problem domain. In 1998 Geva, Malmstrom, & Sitte, (1998) described the Local Cluster (LC) Neural Net. Geva et.al. (1998) showed that the LC network was able to learn / approximate complex functions to a high degree of accuracy. The hidden layer of the LC network is comprised of basis functions, (the local cluster units), that are composed of sigmoid based 'ridge' functions. In the General form of the LC network the ridge functions can be oriented in any direction. We describe RULEX, a technique designed to provide an explanation component for its underlying Local Cluster ANN through the extraction of symbolic rules from the weights of the local cluster units of the trained ANN. RULEX exploits a feature, ie, axis parallel ridge functions, of the Restricted Local Cluster (Geva , Andrews & Geva 2002), that allow hyper-rectangular rules of the form IF ∀ 1 ≤ i ≤ n : xi ∈ [ xi lower , xi upper ] THEN pattern belongs to the target class to be easily extracted from local functions that comprise the hidden layer of the LC network. RULEX is tested on 14 applications available in the public domain. RULEX results are compared with a leading machine learning technique, See5, with RULEX generally performing as well as See5 and in some cases outperforming See5 in predictive accuracy. We describe RULEIN, a rule refinement technique that allows symbolic rules to be converted into the parameters that define local cluster functions. RULEIN allows existing domain knowledge to be captured in the architecture of a LC ANN thus facilitating the first phase of the rule refinement paradigm. RULEIN is tested on a variety of artificial and real world problems. Experimental results indicate that RULEIN is able to satisfy the first requirement of a rule refinement technique by correctly translating a set of symbolic rules into a LC ANN that has the same predictive bahaviour as the set of rules from which it was constructed. Experimental results also show that in the cases where a strong domain theory exists, initializing an LC network using RULEIN generally speeds up network training, produces smaller, more accurate trained networks, with the trained network properly representing the underlying domain theory. In cases where a weak domain theory exists the same results are not always apparent. Experiments with the RULEIN / LC / RULEX rule refinement method show that the method is able to remove inaccurate rules from the initial knowledge base, modify rules in the initial knowledge base that are only partially correct, and learn new rules not present in the initial knowledge base. The combination of RULEIN / LC / RULEX thus is shown to be an effective rule refinement technique for use with a Restricted Local Cluster network.

The contributions of this thesis are an implicit modelling method for the coupled constitutive relations and an energy-based method for material modelling. The two developed methods utilise implicit models to represent material constitutive relations without the requirement of physical parameters. The first method is developed to model coupled constitutive relations using state-space representation with neural networks. State-space representation is employed to express the desired relations in a compact fashion while simultaneously providing the capability of modelling rate- and/or path-dependent behaviour. The employment of neural networks with the generalised state-space representation results in a single implicit model that can be adapted for a broad range of constitutive behaviours. The performance and applicability of the method are highlighted through the applications for various constitutive behaviour of piezoelectric materials, including the effects of hysteresis and cyclic degradation. An energy-based method is subsequently developed for implicit constitutive modelling by utilising the energy principle on a deformed continuum. Two formulations of the proposed method are developed for the modelling of materials with varying nature in directional properties. The first formulation is based on an implicit strain energy density function, represented by a neural network with strain invariants as input, to derive the desired stress-strain relations. The second formulation consists of the derivation of an energy-based performance function for training a neural network that represents the stress-strain relations. The requirement of deriving stress is eliminated in both formulations and this facilitates the use of advanced experimental setup, such as multi-axial load tests or non-standard specimens, to produce the most information for constitutive modelling from a single experiment. A series of numerical studies -- including validation problems and practical cases with actual experimental setup -- have been conducted, the results of which demonstrate the applicability and effectiveness of the proposed method for constitutive modelling on a continuum basis.