L. Neuberg - Academia.edu (original) (raw)

Papers by L. Neuberg

In this paper, we present a model that simulates the behaviour of a heterogenous collection of fi... more In this paper, we present a model that simulates the behaviour of a heterogenous collection of financial traders on a market. Each trader is modelled as an autonomous, interactive agent and the agregation of their behavior results in market behaviour. We specifically look at the role of information arriving at the market and the influence of heterogeneity on market dynamics. The main conclusions are that the quality of the information determines how the market will behave and secondly, heterogeneity is required in order to find the right statistical properties of the price and return time series.

In this paper, we present a classification model to evaluate the performance of companies on the ... more In this paper, we present a classification model to evaluate the performance of companies on the basis of qualitative criteria, such as organizational and managerial variables. The classification model evaluates the eligibility of the company to receive state subsidies for the development of high tech products. We furthermore created a similar model using the backpropagation learning algorithm and compare its

European Journal of Operational Research, 1999

In this paper, we present a classi®cation model to evaluate the performance of companies on the b... more In this paper, we present a classi®cation model to evaluate the performance of companies on the basis of qualitative criteria, such as organizational and managerial variables. The classi®cation model evaluates the eligibility of the company to receive state subsidies for the development of high tech products. We furthermore created a similar model using the backpropagation learning algorithm and compare its classi®cation performance against the linear model. We also focus on the robustness of the two approaches with respect to uncertain information. This research shows that backpropagation neural networks are not superior to LDA-models (Linear Discriminant Analysis), except when they are given highly uncertain information. Ó

Complexity, 2003

In this paper, we present a multi agent system (MAS) simulation of a financial market and investi... more In this paper, we present a multi agent system (MAS) simulation of a financial market and investigate the requirements to obtain realistic data. The model consists of autonomous, interactive agents that buy stock on a financial market. Transaction decisions are based on a number of individual and collective elements. The former being risk aversion and a set of decision rules reflecting their anticipation of the future evolution of prices and dividends. The latter is the information arriving on the market influencing the decision making process of each trader. We specifically look at this process and the following observations hold : The market behaviour is determined by the information arriving at the market and agent heterogeneity is required in order to obtain the right statistical properties of the price and return time series. The observed results are not sensitive to changes in the parameter values.

In this paper, we present a model that simulates the behaviour of a heterogenous collection of na... more In this paper, we present a model that simulates the behaviour of a heterogenous collection of nancial traders on a market. Each trader is modelled as an autonomous, interactive agent and the agregation of their behavior results in market behaviour. We speci cally look at the role of information arriving at the market and the in uence of heterogeneity on market dynamics. The main conclusions are that the quality o f the information determines how the market will behave and secondly, heterogeneity i s required in order to nd the right statistical properties of the price and return time series.

In this paper, we investigate the impact of chaos on the learning process of the XOR-boolean func... more In this paper, we investigate the impact of chaos on the learning process of the XOR-boolean function by backpropagation neural networks. It has been shown previously that such networks exhibit chaotic behavior but it has never been studied whether chaos enhances or prohibits learning. We show that chaos (when learning the XOR-boolean function) does indeed allow learning but our findings do not indicate any positive role of chaos for learning. In particular, we found that the temperature parameter in the backpropagation algorithm causes the parameter regime, as represented by means of a bifurcation diagram, to shift to the right. We furthermore found that as less chaos appears during the learning process, the faster, on the average, a neural network learned the XOR-function.

In training feed-forward neural networks using the backpropagation algorithm, a sensitivity to th... more In training feed-forward neural networks using the backpropagation algorithm, a sensitivity to the values of the parameters of the algorithm has been observed. In particular, it has been observed that this sensitivity with respect to the values of the parameters, such as the learning rate, plays an important role in the final outcome. In this tutorial paper, we will look at neural networks from a dynamical systems point of view and examine its properties. To this purpose, we collect results regarding chaos theory as well as the backpropagation algorithm and establish a relationship between them. We study in detail as an example the learning of the exclusive OR, an elementary Boolean function. The following conclusions hold for our XOR neural network: no chaos appears for learning rates lower than 5, when chaos occurs, it disappears as learning progresses. For non-chaotic learning rates, the network learns faster than for other learning rates for which chaos occurs.

European Journal of Operational Research, 1999

Complexity, 2003