Back-propagation Multilayer Network Research Articles

Using a neural network to backtranslate amino acid sequences

A neural network (NN) was trained on amino and nucleic acid sequences to test the NN’s ability to predict a nucleic acid sequence given only an amino acid sequence. A multi-layer backpropagation network of one hidden layer with 5 to 9 neurons was used. Different network configurations were used with varying numbers of input neurons to represent amino acids, while a constant representation was used for the output layer representing nucleic acids. In the besttrained network, 93% of the overall bases, 85% of the degenerate bases, and 100% of the fixed bases were correctly predicted from randomly selected test sequences. The training set was composed of 60 human sequences in a window of 10 to 25 codons at the coding sequence start site. Different NN configurations involving the encoding of amino acids under increasing window sizes were evaluated to predict the behavior of the NN with a significantly larger training set. This genetic data analysis effort will assist in understanding human gene structure. Benefits include computational tools that could predict more reliably the backtranslation of amino acid sequences useful for Degenerate PCR cloning, and may assist the identification of human gene coding sequences (CDS) from open reading frames in DNA databases.

Stellar spectral classification using principal component analysis and artificial neural networks

A fast and robust method of classifying a library of optical stellar spectra for O to M type stars is presented. The method employs, as tools: (1) principal component analysis (PCA) for reducing the dimensionality of the data and (2) multilayer back propagation network (MBPN) based artificial neural network (ANN) scheme to automate the process of classification. We are able to reduce the dimensionality of the original spectral data to very few components by using PCA and are able to successfully reconstruct the original spectra. A number of NN architectures are used to classify the library of test spectra. Performance of ANN with this reduced dimension shows that the library can be classified to accuracies similar to those achieved by Gulati et al. but with less computational load. Furthermore, the data compression is so efficient that the NN scheme successfully classifies to the desired accuracy for a wide range of architectures. The procedure will greatly improve our capabilities in handling and analysing large spectral data bases of the future.

A transformation strategy for implementing distributed, multilayer feedforward neural networks: Backpropagation transformation

Most artificial neural networks (ANNs) have a fixed topology during learning, and often suffer from a number of shortcomings as a result. Variations of ANNs that use dynamic topologies have shown ability to overcome many of these problems. This paper introduces location-independent transformations (LITs) as a general strategy for implementing distributed feed forward networks that use dynamic topologies (dynamic ANNs) efficiently in parallel hardware. A LIT creates a set of location-independent nodes, where each node computes its part of the network output independent of other nodes, using local information. This type of transformation allows efficient support for adding and deleting nodes dynamically during learning. In particular, this paper presents a LIT that supports both the standard (static) multilayer backpropagation network, and backpropagation with dynamic extensions. The complexity of both learning and execution algorithms is O( q( Nlog M)) for a single pattern, where q is the number of weight layers in the original network, N the number of nodes in the widest node layer in the original network, and M is the number of nodes in the transformed network (which is linear in the number hidden nodes in the original network). This paper extends previous work with 2-weight-layer backpropagation networks.

Solar wind magnetosphere coupling: Predicted and modeled with intelligent hybrid systems

The solar wind-magnetosphere coupling is described as a mapping of the solar-solar wind state (input) to the magnetosphere-ionosphere state (output). The input-state is defined by solar wind parameters and the output-state is defined by geomagnetic disturbance indices. Most often are the geomagnetic disturbance indices D st and AE used. However, a new family of geomagnetic disturbance indices, CO, SO and EO, have been constructed which even might be able to describe the cusp and dayside magnetosphere. As mapper, a multi-layer backpropagation network, an Elman neural network and a radial basis function neural network, were used. Predictions of solar wind parameters and geomagnetic indices D st and AE are presented. The mapper represents a coupling function. It was found that the coupling function, learned by the neural networks, was more accurate than predefined theoretical coupling functions. In the case of modeling, it is therefore very important to explain the mapper and the trained neural network. Several methods are available: By extracting rules and decision trees from neural networks. By studying the prediction accuracy for different combinations of solar wind input parameters and for different coupling functions. By comparison with well-known mathematical methods. Integrating both data-driven and theory-driven methods into intelligent hybrid systems further improves the scientific method of studying the solar wind-magnetosphere coupling. Lund Space Weather Model is such a hybrid system. IHSs are also capable of mapping simultaneous multi-satellite observations. Such a mapping is therefore also suggested to improve the understanding of the solar wind-magnetosphere coupling.

An Adaptive Structure Neural Networks with Application to EEG Automatic Seizure Detection

This paper introduces a new algorithm for adaptively adjusting the structure of a multi-layer back-propagation network. The proposed algorithm belongs to the class of neuron generating strategies as opposed to the class of neuron pruning strategies. Initially a “small” multi-layer perceptron network is selected. The stabilized error is used as an index to determine whether the network needs to generate a new neuron or not. If after a period of learning the error is stabilized, but the error is larger than a desired value, then new neuron(s) is (are) generated. The new neurons are placed at locations that contribute most to the network error behavior through the fluctuation in their input weight vectors. Among the features of the new architecture are its improved performance and generalization capabilities compared to a standard fixed-structure back-propagation network. Application to an electroencephalogram (EEG) automatic epileptic seizure detection is presented to illustrate advantages and capabilities of the proposed algorithm. Using an actual data from five patients it is shown that the proposed approach correctly identifies all true seizures that are also identified by an expert physician. The new algorithm provides a reduction of 60–70% in the training epochs as compared to a back-propagation algorithm. Furthermore, it is shown that by utilizing a new training algorithm it is possible to reduce the false seizure detections to zero while resulting in a 5.1% error in identifying the true seizures. Copyright © 1996 Elsevier Science Ltd

How to built a connectionist idiot (savant)

This paper describes the development of a connectionist model of an idiot savant date calculator using a multi-layer back-propagation network, The model mimics the behaviour of idiot savant date calculators in learning to perform the date calculation task without the need either to develop arithmetical skills or to encode explicit knowledge about regularities in the structure of dates. However, the performance of the model highlights limitations on the use of back-propagation as a general-purpose learning algorithm in complex problem domains. Even with a relatively simple problem like date calculation back-propagation can only succeed when forced to take a highly structured and modular approach to learning.