Neural Networks

We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data. We discuss basic issues in representation and learning, and treat some of the practical issues that arise in fitting networks to data. We also discuss links between neural networks and the general formalism of graphical models.

Chess Endgames and Neural Networks

The existence of endgame databases challenges us to extract higher-grade information and knowledge from their basic data content. Chess players, for example, would like simple and usable endgame theories if such holy grail exists: endgame experts would like to provide such insights and be inspired by computers to do so. Here, we investigate the use of artificial neural networks (NNs) to mine these databases and we report on a first use of NNs on KPK. The results encourage us to suggest further work on chess applications of neural networks and other data-mining techniques.

Neural networks for power systems alarm handling

A multi-layered architecture of self-organizing neural networks is being developed as part of an intelligent alarm processor to analyse a stream of power grid fault messages and provide a suggested diagnosis of the fault location. Feedback concerning the accuracy of the diagnosis is provided by an object-oriented grid simulator which acts as an external supervisor to the learning system. The utilization of artificial neural networks within this environment should result in a powerful generic alarm processor which will not require extensive training by a human expert to produce accurate results.

Stable receding horizon control based on recurrent networks

The last decade has seen the re-emergence of artificial neural networks as an alternative to traditional modelling techniques for the control of nonlinear systems. Numerous control schemes have been proposed and have been shown to work in simulations. However, very few analyses have been made of the working of these networks. The authors show that a receding horizon control strategy based on a class of recurrent networks can stabilise nonlinear systems.

Dynamic knowledge representation in connectionist systems

One of the most pervading concepts underlying computational models of information processing in the brain is linear input integration of rate coded uni-variate information by neurons. After a suitable learning process this results in neuronal structures that statically represent knowledge as a vector of real valued synaptic weights. Although this general framework has contributed to the many successes of connectionism, in this paper we argue that for all but the most basic of cognitive processes, a more complex, multi-variate dynamic neural coding mechanism is required - knowledge should not be spacially bound to a particular neuron or group of neurons. We conclude the paper with discussion of a simple experiment that illustrates dynamic knowledge representation in a spiking neuron connectionist system.

PID autotuning using neural networks and model reference adaptive control

This paper describes the application of artificial neural networks for automatic tuning of PID controllers using the Model Reference Adaptive Control approach. The effectiveness of the proposed method is shown through a simulated application.

Relative order defines a topology for recurrent networks

This paper uses techniques from control theory in the analysis of trained recurrent neural networks. Differential geometry is used as a framework, which allows the concept of relative order to be applied to neural networks. Any system possessing finite relative order has a left-inverse. Any recurrent network with finite relative order also has an inverse, which is shown to be a recurrent network.

Revealing ensemble state transition patterns in multi-electrode neuronal recordings using hidden Markov models

In order to harness the computational capacity of dissociated cultured neuronal networks, it is necessary to understand neuronal dynamics and connectivity on a mesoscopic scale. To this end, this paper uncovers dynamic spatiotemporal patterns emerging from electrically stimulated neuronal cultures using hidden Markov models (HMMs) to characterize multi-channel spike trains as a progression of patterns of underlying states of neuronal activity. However, experimentation aimed at optimal choice of parameters for such models is essential and results are reported in detail. Results derived from ensemble neuronal data revealed highly repeatable patterns of state transitions in the order of milliseconds in response to probing stimuli.

Multiscale evolving complex network model of functional connectivity in neuronal cultures

Cultures of cortical neurons grown on multielectrode arrays exhibit spontaneous, robust and recurrent patterns of highly synchronous activity called bursts. These bursts play a crucial role in the development and topological selforganization of neuronal networks. Thus, understanding the evolution of synchrony within these bursts could give insight into network growth and the functional processes involved in learning and memory. Functional connectivity networks can be constructed by observing patterns of synchrony that evolve during bursts. To capture this evolution, a modelling approach is adopted using a framework of emergent evolving complex networks and, through taking advantage of the multiple time scales of the system, aims to show the importance of sequential and ordered synchronization in network function.

An overview of the use of neural networks for data mining tasks

In the recent years, the area of data mining has been experiencing considerable demand for technologies that extract knowledge from large and complex data sources. There has been substantial commercial interest as well as active research in the area that aim to develop new and improved approaches for extracting information, relationships, and patterns from large datasets. Artificial neural networks (NNs) are popular biologically-inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas, including science, engineering, medicine, business, banking, telecommunication, and many other fields. This paper highlights from a data mining perspective the implementation of NN, using supervised and unsupervised learning, for pattern recognition, classification, prediction, and cluster analysis, and focuses the discussion on their usage in bioinformatics and financial data analysis tasks. © 2012 Wiley Periodicals, Inc.

The influence of ARIMA-GARCH parameters in feed forward neural networks prediction

The objective of this article is to find out the influence of the parameters of the ARIMA-GARCH models in the prediction of artificial neural networks (ANN) of the feed forward type, trained with the Levenberg-Marquardt algorithm, through Monte Carlo simulations. The paper presents a study of the relationship between ANN performance and ARIMA-GARCH model parameters, i.e. the fact that depending on the stationarity and other parameters of the time series, the ANN structure should be selected differently. Neural networks have been widely used to predict time series and their capacity for dealing with non-linearities is a normally outstanding advantage. However, the values of the parameters of the models of generalized autoregressive conditional heteroscedasticity have an influence on ANN prediction performance. The combination of the values of the GARCH parameters with the ARIMA autoregressive terms also implies in ANN performance variation. Combining the parameters of the ARIMA-GARCH models and changing the ANN`s topologies, we used the Theil inequality coefficient to measure the prediction of the feed forward ANN.

A neural networks study of quinone compounds with trypanocidal activity

This work investigates neural network models for predicting the trypanocidal activity of 28 quinone compounds. Artificial neural networks (ANN), such as multilayer perceptrons (MLP) and Kohonen models, were employed with the aim of modeling the nonlinear relationship between quantum and molecular descriptors and trypanocidal activity. The calculated descriptors and the principal components were used as input to train neural network models to verify the behavior of the nets. The best model for both network models (MLP and Kohonen) was obtained with four descriptors as input. The descriptors were T(5) (torsion angle), QTS1 (sum of absolute values of the atomic charges), VOLS2 (volume of the substituent at region B) and HOMO-1 (energy of the molecular orbital below HOMO). These descriptors provide information on the kind of interaction that occurs between the compounds and the biological receptor. Both neural network models used here can predict the trypanocidal activity of the quinone compounds with good agreement, with low errors in the testing set and a high correctness rate. Thanks to the nonlinear model obtained from the neural network models, we can conclude that electronic and structural properties are important factors in the interaction between quinone compounds that exhibit trypanocidal activity and their biological receptors. The final ANN models should be useful in the design of novel trypanocidal quinones having improved potency.