The approach of H. Bersini to shape-spaces and in particular his definition of affinity are analysed. It is shown that the definition of the affinity function in Bersini style implies a special form of an affinity region, namely a rhombus. However, variants of the function can be defined with rectangular or square but rotated affinity regions. In all cases, the affinity function has the form of a pyramid over the affinity region. The definition of the affinity function can be modified in such a way that it describes a lopsided pyramid. Experimental results with a reimplementation of Bersini’s simulation procedure show that the form of the affinity region has a strong influence on the form of the recognition/tolerance separation of the shape-space.

The purpose of this work is to propose an immune-inspired setup to use a self-organizing map as a computational model for the interaction of antigens and antibodies. The proposed approach may be used as a part in other immune algorithms, or can possibly be used to detect anomalies in time series data.

The kernel perceptron is one of the simplest and fastest kernel machines, its performance, however, is inferior to other well known kernel machines. We introduce an algorithm that combines several approaches, mainly Herbrich's large-scale Bayes point machine and the soft perceptron in order to improve the kernel perceptron. Our experiments, which were based on standard benchmark datasets, show that the performance of the perceptron can be improved significantly with similar computational effort.

In 1989, Singhal and Wu showed that training a feed forward neural network can be viewed as an identification problem for a nonlinear dynamic system using an extended Kalman filter algorithm, which can converge in few iterations. In this paper, a new type of optimal bounding ellipsoid (OBE) algorithm is presented, which is a set-membership identification algorithm based on set theory, and it is shown how it can be used for training feedforward neural networks. The algorithm is compared with backpropagation (BP) and extended Kalman filter (EKF) algorithms and simulation results are presented.

Recursive auto-associative memory networks (RAAM) are neural networks that can be trained to represent structured information. After training, this information can be retrieved following its inner structure. By now, RAAM networks were applied only to syntactical expressions like parse trees of natural language sentences or logical terms. In this paper it is shown how they can be used for representing vector graphics that are given as a tree. For this purpose we developed name RAAM networks (NRAAM) which are more suitable for the training of complex information than normal RAAMs.

Hebbian Learning is well-known for training of associative networks whereas recursive auto-associative memory (RAAM) learning uses auto-associative networks which are trained to represent structured information like parse trees of natural sentences or logical terms. In this paper Hebbian learning is used for representing structured information in terms of vector graphic. The resulting networks are holistically computed. Furthermore, a theorem relating bipolar Hebbian learning is proved.

CAUSA is a knowledge acquisition tool which supports the incremental modeling of complex dynamic systems during the whole knowledge acquisition task. It provides an environment for the modeling and simulation of dynamic systems on a quantitative level. The environment provides a conceptual framework which includes primitives like objects, processes, and causal dependencies, allowing for the modeling of a broad class of complex systems. Simulation allows for the quantitative and qualitative inspection and empirical investigation of the behavior of the modeled system. CAUSA is implemented in Knowledge-Craft and runs on a Symbolics 3640.