A Neural Model for Category Learning

Reilly, Douglas L.; Cooper, Leon N.; Elbaum, C.

doi:10.1142/9789812795885_0018

Cited by 27 publications

(30 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this way the network presents the first step in constructing a more interactive recognition system. In comparison to Nearest neighbor rule (Cover and Hart, 1967) and RCE network (Reilly et al, 1982;Scofield et al, 1987), our approach offers several advantages: it is computationally efficient, it is optimal in the Bayesian sense and there are no external parameters associated with proto-type regions. In addition, the algorithm for constructing prototype regions is extremely easy to implement and offers a unique partitioning of the feature space regardless of the order in which the training samples are presented to the system.…”

Section: Properties Of the System And Resultsmentioning

confidence: 99%

Reducing the cognitive workload while operating in complex sensory environments

Cooper¹,

Neskovic²

2004

PsycEXTRA Dataset

Self Cite

View full text Add to dashboard Cite

Section: Properties Of the System And Resultsmentioning

confidence: 99%

Reducing the cognitive workload while operating in complex sensory environments

Cooper¹,

Neskovic²

2004

PsycEXTRA Dataset

Self Cite

View full text Add to dashboard Cite

“…(15). Among those methods listed, GDALR is the best when considering together all of the computation time and memory requirements, sensitivity to the initial centers and radii, and training and test performances.…”

Section: Gradient Descent Solution For the Spherical Classifier Designmentioning

confidence: 99%

“…III) Depending on the choice of kernel and the kernel's parameter, the distance order among the samples may not be preserved while carrying them into the feature space by the nonlinear mapping defined by the chosen kernel [12][13][14][15]. This means that the inverse image of the optimal separating hyperplane found in the feature space may be far away from the optimal separating surface in the input data space.…”

Section: Introductionmentioning

confidence: 99%

A penalty function method for designing efficient robust classifiers with input space optimal separating surfaces

Uçar¹,

Demir²,

Güzeliş³

2014

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper considers robust classification as a constrained optimization problem. Where the constraints are nonlinear, inequalities defining separating surfaces, whose half spaces include or exclude the data depending on their classes and the cost, are used for attaining robustness and providing the minimum volume regions specified by the half spaces of the surfaces. The constraints are added to the cost using penalty functions to get an unconstrained problem for which the gradient descent method can be used. The separating surfaces, which are aimed to be found in this way, are optimal in the input data space in contrast to the conventional support vector machine (SVM) classifiers designed by the Lagrange multiplier method, which are optimal in the (transformed) feature space. Two types of surfaces, namely hyperellipsoidal and Gaussian-based surfaces created by radial basis functions (RBFs), are focused on in this paper due to their generality. Ellipsoidal classifiers are trained in 2 stages: a spherical surface is found in the first stage, and then the centers and the radii found in the first stage are taken as the initial input for the second stage to find the center and covariance matrix parameters of the ellipsoids. The penalty function approach to the design of robust classifiers enables the handling of multiclass classification. Compared to SVMs, multiple-kernel SVMs, and RBF classifiers, the proposed classifiers are found to be more efficient in terms of the required training time, parameter setting time, testing time, memory usage, and generalization error, especially for medium to large datasets. RBF-based input space optimal classifiers are also introduced for problems that are far from ellipsoidal, e.g., 2 Spirals.

show abstract

“…Step 4: Back propagation learning Mandic (2001), Reilly (1982 algorithm is selected for training the network…”

Section: 11prediction Of Thermo Physical Propertiesmentioning

confidence: 99%

Artificial Neural Networks for the Prediction of Thermo Physical Properties of Liquid Mixtures

Baskaran¹,

Arunachalam²,

Manjunath³

et al. 2008

CIS

View full text Add to dashboard Cite

A predictive method based on Artificial networks has been developed for the thermophysical properties of binary liquid mixtures at (303.15, 313.15 and 323.15) K. In method 1, a committee ANN was trained using 5 physical properties combined with absolute temperature as its input to predict thermo physical properties of liquid mixtures. Using these data, predicted values were determined for intermediate mole fraction of different systems without conducting experiments. In method 2, a committee ANN was trained using mole fraction and molecular weight as its input to predict the thermo physical properties of liquid mixtures. The five physical properties of five binary mixtures were taken for this study along with their molecular weights. ANN with back-propagation algorithm is proposed, for Multi-pass Turning Operation and developed in MATLAB. Compared to other prediction techniques, the proposed ANN approach is highly accurate and error is <1%.

show abstract

A Neural Model for Category Learning

Cited by 27 publications

References 0 publications

Reducing the cognitive workload while operating in complex sensory environments

Reducing the cognitive workload while operating in complex sensory environments

A penalty function method for designing efficient robust classifiers with input space optimal separating surfaces

Artificial Neural Networks for the Prediction of Thermo Physical Properties of Liquid Mixtures

Contact Info

Product

Resources

About