SEARCH · PubMed Health

Results for “Multilayer Perceptrons”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources

PubMed2000

Auto-calibration and -compensation of a capacitive pressure sensor using multilayer perceptrons

Using multilayer perceptrons (MLPs), a smart model for a capacitive pressure sensor (CPS) is proposed. When the ambient temperature changes, the nonlinear response characteristics of a CPS may vary widely. Under such conditions, calibration of the sensor and compensation of the nonlinear sensor characteristics to obtain correct readout becomes a difficult task. The proposed MLP model can provide automatic nonlinear compensation and calibration of the CPS characteristics. A microcontroller unit (MCU)-based implementation scheme for this model is also considered. Simulation results show that this model can estimate the pressure with a maximum full-scale error of +/- 1% over a variation of temperature from -50 to 150 degrees C.

Journal Article↗

PubMed2001

DMP3: a dynamic multilayer perceptron construction algorithm.

This paper presents DMP3 (Dynamic Multilayer Perceptron 3), a multilayer perceptron (MLP) constructive training method that constructs MLPs by incrementally adding network elements of varying complexity to the network. DMP3 differs from other MLP construction techniques in several important ways, and the motivation for these differences are given. Information gain rather than error minimization is used to guide the growth of the network, which increases the utility of newly added network elements and decreases the likelihood that a premature dead end in the growth of the network will occur. The generalization performance of DMP3 is compared with that of several other well-known machine learning and neural network learning algorithms on nine real world data sets. Simulation results show that DMP3 performs better (on average) than any of the other algorithms on the data sets tested. The main reasons for this result are discussed in detail.

Algorithms↗

PubMed1999

Forecasting chaotic cardiovascular time series with an adaptive slope multilayer perceptron neural network.

A multilayer perceptron (MLP) network architecture has been formulated in which two adaptive parameters, the scaling and translation of the postsynaptic function at each node, are allowed to adjust iteratively by gradient-descent. The algorithm has been employed to predict experimental cardiovascular time series, following systematic reconstruction of the strange attractor of the training signal. Comparison with a standard MLP employing identical numbers of nodes and weight learning rates demonstrates that the adaptive approach provides an efficient modification of the MLP that permits faster learning. Thus, for an equivalent number of training epochs there was improved accuracy and generalization for both one- and k-step ahead prediction. The applicability of the methodology is demonstrated for a set of monotonic postsynaptic functions (sigmoidal, upper bounded, and nonbounded). The approach is computationally inexpensive as the increase in the parameter space of the network compared to a standard MLP is small.

Algorithms↗

PubMed1995

Human chromosome classification using multilayer perceptron neural network.

A multilayer perceptron (MLP) neural network (NN) has been studied for human chromosome classification. Only 10-20 examples were required for the MLP NN to reach its ultimate performance classifying chromosomes of 5 types. The empirical dependence of the entropic error on the number of examples was found to be highly comparable to the 1/t function. The principal component analysis (PCA) was used, both for network initialization and for feature reduction purposes. The PCA demonstrated the importance of retaining most of the image information whenever small training sets are used. The MLP NN classifier outperformed the Bayes piecewise classifier for all the cases tested. The MLP classifier was found to be almost unsusceptible to the ratio of the number of training vectors to the number of features, whereas the piecewise classifier was highly dependent on this ratio.

Algorithms↗

PubMed1988

Auto-association by multilayer perceptrons and singular value decomposition.

The multilayer perceptron, when working in auto-association mode, is sometimes considered as an interesting candidate to perform data compression or dimensionality reduction of the feature space in information processing applications. The present paper shows that, for auto-association, the nonlinearities of the hidden units are useless and that the optimal parameter values can be derived directly by purely linear techniques relying on singular value decomposition and low rank matrix approximation, similar in spirit to the well-known Karhunen-Loève transform. This approach appears thus as an efficient alternative to the general error back-propagation algorithm commonly used for training multilayer perceptrons. Moreover, it also gives a clear interpretation of the rôle of the different parameters.

Mathematics↗

PubMed1997

Selecting optimal experiments for multiple output multilayer perceptrons.

Where should a researcher conduct experiments to provide training data for a multilayer perceptron? This question is investigated, and a statistical method for selecting optimal experimental design points for multiple output multilayer perceptrons is introduced. Multiple class discrimination problems are examined using a framework in which the multilayer perceptron is viewed as a multivariate nonlinear regression model. Following a Bayesian formulation for the case where the variance-covariance matrix of the responses is unknown, a selection criterion is developed. This criterion is based on the volume of the joint confidence ellipsoid for the weights in a multilayer perceptron. An example is used to demonstrate the superiority of optimally selected design points over randomly chosen points, as well as points chosen in a grid pattern. Simplification of the basic criterion is offered through the use of Hadamard matrices to produce uncorrelated outputs.

Algorithms↗

PubMed2004

Complexity of error hypersurfaces in multilayer perceptrons.

Error hypersurfaces are very valuable to study because of their unique status in multilayer perceptron research. Given the architecture of a multilayer perceptron, if the pattern sets are different, so are the respective error hypersurfaces in the multilayer perceptron. Using the theory of groups and Polya Theorem, this paper constructs classes of congruent pattern sets and classes of congruent error hypersurfaces, and proves that the number of classes of congruent pattern sets is equal to the number of congruent error hypersurfaces. Calculation results lead to much fewer classes of congruent error hypersurfaces than the total error hypersurfaces, and show that as the input dimension N increases, the former number increases at a much lower rate than the latter number, thus simplifying the understanding of the complexity of classes of error hypersurfaces.

Algorithms↗

PubMed2001

Efficiently learning multilayer perceptrons.

A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their target outputs. For large networks our procedure needs far fewer examples to achieve good generalization than traditional on-line algorithms.

Algorithms↗

PubMedDate not supplied

Bayesian applications of belief networks and multilayer perceptrons for ovarian tumor classification with rejection.

Incorporating prior knowledge into black-box classifiers is still much of an open problem. We propose a hybrid Bayesian methodology that consists in encoding prior knowledge in the form of a (Bayesian) belief network and then using this knowledge to estimate an informative prior for a black-box model (e.g. a multilayer perceptron). Two technical approaches are proposed for the transformation of the belief network into an informative prior. The first one consists in generating samples according to the most probable parameterization of the Bayesian belief network and using them as virtual data together with the real data in the Bayesian learning of a multilayer perceptron. The second approach consists in transforming probability distributions over belief network parameters into distributions over multilayer perceptron parameters. The essential attribute of the hybrid methodology is that it combines prior knowledge and statistical data efficiently when prior knowledge is available and the sample is of small or medium size. Additionally, we describe how the Bayesian approach can provide uncertainty information about the predictions (e.g. for classification with rejection). We demonstrate these techniques on the medical task of predicting the malignancy of ovarian masses and summarize the practical advantages of the Bayesian approach. We compare the learning curves for the hybrid methodology with those of several belief networks and multilayer perceptrons. Furthermore, we report the performance of Bayesian belief networks when they are allowed to exclude hard cases based on various measures of prediction uncertainty.

Bayes Theorem↗

PubMed1995

Multilayer perceptrons to approximate complex valued functions.

In this paper the approximation capabilities of different structures of complex feedforward neural networks, reported in the literature, have been theoretically analyzed. In particular a new density theorem for Complex Multilayer Perceptrons with complex valued non-analytical sigmoidal activation functions has been proven. Such a result makes Multilayer Perceptrons with complex valued neurons universal interpolators of continuous complex valued functions. Moreover the approximation properties of superpositions of analytic activation functions have been investigated, proving that such combinations are not dense in the set of continuous complex valued functions. Several numerical examples have also been reported in order to show the advantages introduced by Complex Multilayer Perceptrons in terms of computational complexity with respect to the classical real MLP.

Neural Networks, Computer↗

PubMed1997

Multilayer Perceptrons to Approximate Quaternion Valued Functions.

In this paper a new type of multilayer feedforward neural network is introduced. Such a structure, called hypercomplex multilayer perceptron (HMLP), is developed in quaternion algebra and allows quaternionic input and output signals to be dealt with, requiring a lower number of neurons than the real MLP, thus providing a reduced computational complexity. The structure introduced represents a generalization of the multilayer perceptron in the complex space (CMLP) reported in the literature. The fundamental result reported in the paper is a new density theorem which makes HMLPs universal interpolators of quaternion valued continuous functions. Moreover the proof of the density theorem can be restricted in order to formulate a density theorem in the complex space. Due to the identity between the quaternion and the four-dimensional real space, such a structure is also useful to approximate multidimensional real valued functions with a lower number of real parameters, decreasing the probability of being trapped in local minima during the learning phase. A numerical example is also reported in order to show the efficiency of the proposed structure. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.

Journal Article↗

PubMed1998

Complexity issues in natural gradient descent method for training multilayer perceptrons.

The natural gradient descent method is applied to train an n-m-1 multilayer perceptron. Based on an efficient scheme to represent the Fisher information matrix for an n-m-1 stochastic multilayer perceptron, a new algorithm is proposed to calculate the natural gradient without inverting the Fisher information matrix explicitly. When the input dimension n is much larger than the number of hidden neurons m, the time complexity of computing the natural gradient is O(n).

Learning↗

PubMed2003

Approximation by fully complex multilayer perceptrons.

We investigate the approximation ability of a multilayer perceptron (MLP) network when it is extended to the complex domain. The main challenge for processing complex data with neural networks has been the lack of bounded and analytic complex nonlinear activation functions in the complex domain, as stated by Liouville's theorem. To avoid the conflict between the boundedness and the analyticity of a nonlinear complex function in the complex domain, a number of ad hoc MLPs that include using two real-valued MLPs, one processing the real part and the other processing the imaginary part, have been traditionally employed. However, since nonanalytic functions do not meet the Cauchy-Riemann conditions, they render themselves into degenerative backpropagation algorithms that compromise the efficiency of nonlinear approximation and learning in the complex vector field. A number of elementary transcendental functions (ETFs) derivable from the entire exponential function e(z) that are analytic are defined as fully complex activation functions and are shown to provide a parsimonious structure for processing data in the complex domain and address most of the shortcomings of the traditional approach. The introduction of ETFs, however, raises a new question in the approximation capability of this fully complex MLP. In this letter, three proofs of the approximation capability of the fully complex MLP are provided based on the characteristics of singularity among ETFs. First, the fully complex MLPs with continuous ETFs over a compact set in the complex vector field are shown to be the universal approximator of any continuous complex mappings. The complex universal approximation theorem extends to bounded measurable ETFs possessing a removable singularity. Finally, it is shown that the output of complex MLPs using ETFs with isolated and essential singularities uniformly converges to any nonlinear mapping in the deleted annulus of singularity nearest to the origin.

Neural Networks, Computer↗

PubMed2005

Efficient training of multilayer perceptrons using principal component analysis.

A training algorithm for multilayer perceptrons is discussed and studied in detail, which relates to the technique of principal component analysis. The latter is performed with respect to a correlation matrix computed from the example inputs and their target outputs. Typical properties of the training procedure are investigated by means of a statistical physics analysis in models of learning regression and classification tasks. We demonstrate that the procedure requires by far fewer examples for good generalization than traditional online training. For networks with a large number of hidden units we derive the training prescription which achieves, within our model, the optimal generalization behavior.

Journal Article↗

PubMed2006

Statistical mechanics of lossy compression using multilayer perceptrons.

Statistical mechanics is applied to lossy compression using multilayer perceptrons for unbiased Boolean messages. We utilize a treelike committee machine (committee tree) and treelike parity machine (parity tree) whose transfer functions are monotonic. For compression using a committee tree, a lower bound of achievable distortion becomes small as the number of hidden units K increases. However, it cannot reach the Shannon bound even where K-->infinity. For a compression using a parity tree with K> or =2 hidden units, the rate distortion function, which is known as the theoretical limit for compression, is derived where the code length becomes infinity.

Journal Article↗

PubMed2000

Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network.

OBJECTIVES: To assess whether an artificial neural network (multilayer perceptron, MLP) and logistic regression (LR) could eliminate more false-positive prostate-specific antigen (PSA) results than the proportion of free PSA in a prostate cancer screening. METHODS: MLP and LR models were constructed on the basis of data on total PSA, the proportion of free PSA, digital rectal examination (DRE), and prostate volume from 656 consecutive men (aged 55 to 67 years) with total serum PSA concentrations of 4 to 10 ng/mL in the randomized population-based prostate cancer screening study in Finland. The MLP and LR models were validated using the "leave-one-out" method. RESULTS: Of the 656 men, 23% had prostate cancer and 77% had either normal prostatic histology or a benign disease. At a 95% sensitivity level, 19% of the false-positive PSA results could be eliminated by using the proportion of free PSA versus 24% with the LR model and 33% with the MLP model (P < 0.001). At 80% to 99% sensitivity levels, the accuracy of the MLP and LR models was significantly higher than that of the proportion of free PSA. At 89% to 99% sensitivities, the accuracy of the MLP was higher than that of LR (P </= 0.001). CONCLUSIONS: At clinically relevant sensitivity levels, the MLP and LR models based on total PSA, the proportion of free PSA, DRE, and prostate volume could reduce the number of unnecessary biopsies significantly better than the proportion of free PSA alone in men with total PSA levels in the range 4 to 10 ng/mL.

Aged↗

PubMed2006

Optimized multilayer perceptrons for molecular classification and diagnosis using genomic data.

MOTIVATION: Multilayer perceptrons (MLP) represent one of the widely used and effective machine learning methods currently applied to diagnostic classification based on high-dimensional genomic data. Since the dimensionalities of the existing genomic data often exceed the available sample sizes by orders of magnitude, the MLP performance may degrade owing to the curse of dimensionality and over-fitting, and may not provide acceptable prediction accuracy. RESULTS: Based on Fisher linear discriminant analysis, we designed and implemented an MLP optimization scheme for a two-layer MLP that effectively optimizes the initialization of MLP parameters and MLP architecture. The optimized MLP consistently demonstrated its ability in easing the curse of dimensionality in large microarray datasets. In comparison with a conventional MLP using random initialization, we obtained significant improvements in major performance measures including Bayes classification accuracy, convergence properties and area under the receiver operating characteristic curve (A(z)). SUPPLEMENTARY INFORMATION: The Supplementary information is available on http://www.cbil.ece.vt.edu/publications.htm

Biomarkers, Tumor↗

PubMed2006

Ethyl alcohol production optimization by coupling genetic algorithm and multilayer perceptron neural network.

In this present article, genetic algorithms and multilayer perceptron neural network (MLPNN) have been integrated in order to reduce the complexity of an optimization problem. A data-driven identification method based on MLPNN and optimal design of experiments is described in detail. The nonlinear model of an extractive ethanol process, represented by a MLPNN, is optimized using real-coded and binary-coded genetic algorithms to determine the optimal operational conditions. In order to check the validity of the computational modeling, the results were compared with the optimization of a deterministic model, whose kinetic parameters were experimentally determined as functions of the temperature.

Algorithms↗