International Journal of Computational Intelligence and Applications

This paper brings a detailed mathematical description of an artificial immune network model, named aiNet. The model is implemented in association with graph concepts and hierarchical clustering techniques, and is proposed to perform machine learning, data compression and cluster analysis. Pictorial representations for the aiNet basic units and typical architectures are introduced. The proposed immune network was primarily compared on a theoretical basis with well-known artificial neural networks. Then, the aiNet was applied to a non-linearly separable benchmark and a real-world problem, and the results were compared with that of the self-organizing feature map and with others already presented in the literature.

In this paper, we will begin with an overview of functional decomposition algorithms based on different graph coloring heuristics. We will then discuss the applications of decomposition strategy for the computer aided design of digital circuits and for the supervised learning of neural networks. While decomposition was used successfully in logic synthesis for several years, its application in the area of neural networks is a novel and promising approach. The computer experiments will show significant benefits in mini mization of silicon space required for digital circuit implementation as well as in reduction of training time for neural networks.

Autonomous robots are unsuccessful at operating in complex, unconstrained environments. They lack the ability to learn about the physical behavior of different objects through the use of vision. We combine Bayesian networks and qualitative spatial representation to learn general physical behavior by visual observation. We input training scenarios that allow the system to observe and learn normal physical behavior. The position and velocity of the visible objects are represented as qualitative states. Transitions between these states over time are entered as evidence into a Bayesian network. The network provides probabilities of future transitions to produce predictions of future physical behavior. We use test scenarios to determine how well the approach discriminates between normal and abnormal physical behavior and actively predicts future behavior. We examine the ability of the system to learn three naive physical concepts, "no action at a distance", "solidity" and "movement on continuous paths". We conclude that the combination of qualitative spatial representations and Bayesian network techniques is capable of learning these three rules of naive physics.

Prediction in real-time image sequences is a key-feature for visual servoing applications. It is used to compensate for the time-delay introduced by the image feature extraction process in the visual feedback loop. In order to track targets in a three-dimensional space in real-time with a robot arm, the target's movement and the robot end-effector's next position are predicted from the previous movements. A modular prediction architecture is presented, which is based on the Kalman filtering principle. The Kalman filter is an optimal stochastic estimation technique which needs an accurate system model and which is particularly sensitive to noise. The performances of this filter diminish with nonlinear systems and with time-varying environments. Therefore, we propose an adaptive Kalman filter using the modular framework of mixture of experts regulated by a gating network. The proposed filter has an adaptive state model to represent the system around its current state as close as possible. Different realizations of these state model adaptive Kalman filters are organized according to the divide-and-conquer principle: they all participate to the global estimation and a neural network mediates their different outputs in an unsupervised manner and tunes their parameters. The performances of the proposed approach are evaluated in terms of precision, capability to estimate and compensate abrupt changes in targets trajectories, as well as to adapt to time-variant parameters. The experiments prove that, without the use of models (e.g. the camera model, kinematic robot model, and system parameters) and without any prior knowledge about the targets movements, the predictions allow to compensate for the time-delay and to reduce the tracking error.

In general, in competitive learning the requirement for the initial number of prototypes is a difficult task, as we do not usually know the number of clusters in the input data a priori. The behavior and performance of the competitive algorithms are very sensitive to the initial locations and number of the prototypes. In this paper after investigating several important competitive learning paradigms, we present compensation techniques for overcoming the problems in competitive learning. Our experimental results show that competition with compensation can improve the performance of the learning algorithm.