Agent-Based Optimization for Large Scale WLAN Design , by A. M. Gibney, M. Klepal, and D. Pesch, IEEE Transactions on Evolutionary Computation, Vol. 15, No. 4, August 2011, pp. 470-486.

Digital Object Identifier: 10.1109/TAMD.2011.2109714
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5963816

"The complex nature of wireless local area networks (WLAN) design has led many of the deployments being done in an ad-hoc fashion without efficient design methodologies. Although this approach may work for a small environment with a small number of access points, it is infeasible to use such a process when designing a larger wireless infrastructure. Due to the low cost that is indicative of WLAN deployments, many practitioners view formal optimization techniques as being too complex and costly to implement. There have been a number of research works that investigate the use of formal optimization techniques for the accurate design of a WLAN. Unfortunately, the approaches taken do not address one major issue when designing a complex and demanding wireless network infrastructure, namely scalability. An optimization algorithm must consider a multitude of design criteria and therefore needs to be scalable to be successfully applied to large scenarios. The main contribution of the work presented in this paper is the development of a scalable optimization algorithm based on the tools of distributed artificial intelligence, which overcomes the failings of current approaches and can be utilized for WLAN design regardless of size or complexity of site specific requirements..." Free Download

Dynamic Neural Fields as Building Blocks of a Cortex-Inspired Architecture for Robotic Scene Representation , by S. Zibner, C. Faubel, I. Iossifidis, and G. Schöner, IEEE Transactions on Autonomous Mental Development, Vol. 3, No. 1, March 2011, pp. 74-91.

Digital Object Identifier: 10.1109/TAMD.2011.2109714
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5709974

"Based on the concepts of dynamic field theory (DFT), we present an architecture that autonomously generates scene representations by controlling gaze and attention, creating visual objects in the foreground, tracking objects, reading them into working memory, and taking into account their visibility. At the core of this architecture are three-dimensional dynamic neural fields (DNFs) that link feature to spatial information. These three-dimensional fields couple into lower dimensional fields, which provide the links to the sensory surface and to the motor systems. We discuss how DNFs can be used as building blocks for cognitive architectures, characterize the critical bifurcations in DNFs, as well as the possible coupling structures among DNFs. In a series of robotic experiments, we demonstrate how the DNF architecture provides the core functionalities of a scene representation.." Free Download

Approximate Confidence and Prediction Intervals for Least Squares Support Vector Regression , by Kris De Brabanter, Jos De Brabanter, Johan A. K. Suykens, and Bart De Moor, IEEE Transactions on Neural Network, Vol. 22, No. 1, January 2011, pp. 110-120.

Digital Object Identifier: 10.1109/TNN.2010.2087769
URL: http://ieeexplore.ieee.org/iel5/72/4359168
/05617284.pdf?arnumber=5617284

"Bias-corrected approximate 100(1 - a)% pointwise and simultaneous confidence and prediction intervals for least squares support vector machines are proposed. A simple way of determining the bias without estimating higher order derivatives is formulated. A variance estimator is developed that works well in the homoscedastic and heteroscedastic case. In order to produce simultaneous confidence intervals, a simple Sidák correction and a more involved correction (based on upcrossing theory) are used. The obtained confidence intervals are compared to a state-of-the-art bootstrap-based method. Simulations show that the proposed method obtains similar intervals compared to the bootstrap at a lower computational cost." Free Download

Automatic Generation of Game Level Solutions as Storyboards , by D. Pizzi, J. Lugrin, A. Whittaker, and M. Cavazza, IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 3, September 2010, pp. 149-161.

Digital Object Identifier: 10.1109/TCIAIG.2010.2070066
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5557763

"Game programmers rely on artificial intelligence techniques to encode characters' behaviors initially specified by game designers. Although significant efforts have been made to assist their collaboration, the formalization of behaviors remains a time-consuming process during the early stages of game development. We propose an authoring tool allowing game designers to formalize, visualize, modify, and validate game level solutions in the form of automatically generated storyboards. This system uses planning techniques to produce a level solution consistent with gameplay constraints. The main planning agent corresponds to the player character, and the system uses the game actions as planning operators and level objectives as goals to plan the level solutions. Generated solutions are presented as 2-D storyboards similar to comic strips. We present in this paper the first version of a fully implemented prototype as well as examples of generated storyboards, adapted from the original design documents of the blockbuster game Hitman." Free Download

Granular Knowledge Representation and Inference Using Labels and Label Expressions , by J. Lawry and Y. Tang, IEEE Transactions on Fuzzy Systems, Vol. 18, No. 3, June 2010, pp. 500-514.

Digital Object Identifier: 10.1109/TFUZZ.2010.2048218
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5447687

"This paper is a review of the label semantics framework as an epistemic approach to modeling granular information represented by linguistic labels and label expressions. The focus of label semantics is on the decision-making process that a rational communicating agent must undertake in order to establish which available labels can be appropriately used to describe their perceptual information in such a way as they are consistent with the linguistic conventions of the population. As such, it provides an approach to characterizing the relationship between labels and the underlying perceptual domain which, we propose, lies at the heart of what is meant by information granules. Furthermore, it is then shown that there is an intuitive relationship between label semantics and prototype theory, which provides a clear link with Zadeh's original conception of information granularity. For information propagation, linguistic mappings are introduced, which provide a mechanism to infer labeling information about a decision variable from the available labeling information about a set of input variables. Finally, a decision-making process is outlined whereby from linguistic descriptions of input variables, we can infer a linguistic description of the decision variable and, where required, select a single expression describing that variable or a single estimated value." Free Download

Benefits of a Population: Five Mechanisms that Advantage Population-Based Algorithms , by A. Pru?gel-Bennett, IEEE Transactions on Evolutionary Computation, Vol. 14, No. 4, August 2010, pp. 500-517.

Digital Object Identifier: 10.1109/TEVC.2009.2039139
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5439829

This paper identifies five distinct mechanisms by which a population-based algorithm might have an advantage over a solo-search algorithm in classical optimization. These mechanisms are illustrated through a number of toy problems. Simulations are presented comparing different search algorithms on these problems. The plausibility of these mechanisms occurring in classical optimization problems is discussed. The first mechanism we consider relies on putting together building blocks from different solutions. This is extended to include problems containing critical variables. The second mechanism is the result of focusing of the search caused by crossover. Also discussed in this context is strong focusing produced by averaging many solutions. The next mechanism to be examined is the ability of a population to act as a low-pass filter of the landscape, ignoring local distractions. The fourth mechanism is a population's ability to search different parts of the fitness landscape, thus hedging against bad luck in the initial position or the decisions it makes. The final mechanism is the opportunity of learning useful parameter values to balance exploration against exploitation. Free Download

Regularized Negative Correlation Learning for Neural Network Ensembles , by H. Chen and X. Yao, IEEE Transactions on Neural Networks, Vol. 20, No. 12, December 2009, pp. 1962-1979.
Digital Object Identifier: 10.1109/TNN.2009.2034144
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=
&arnumber=5337957

"Negative correlation learning (NCL) is analyzed to reveal that the training of NCL corresponds to training the entire ensemble as a single learning machine that only minimizes the MSE without regularization. This analysis explains the reason why NCL is prone to overfitting the noise in the training set." ... Free Download

R-IAC: Robust Intrinsically Motivated Exploration and Active Learning, by A. Baranes and P.-Y. Oudeyer,
IEEE Transactions on Autonomous Mental Development, Vol. 1, No. 3, October 2009, pp. 155 - 169.
Digital Object Identifier : 10.1109/TAMD.2009.2037513

"Intelligent adaptive curiosity (IAC) was initially introduced as a developmental mechanism allowing a robot to self-organize developmental trajectories of increasing complexity without preprogramming the particular developmental stages." ... Free Download