Quasi-Lagrangian neural network for convex quadratic optimization.

A new neural network for convex quadratic optimization is presented in this brief. The proposed network can handle both equality and inequality constraints, as well as bound constraints on the optimization variables. It is based on the Lagrangian approach, but exploits a partial dual method in order to keep the number of variables at minimum. The dynamic evolution is globally convergent and the steady-state solutions satisfy the necessary and sufficient conditions of optimality. The circuit implementation is simpler with respect to existing solutions for the same class of problems. The validity of the proposed approach is verified through some simulation examples.

Retinal blood vessel segmentation using line operators and support vector classification.

In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. A line detector, previously used in mammography, is applied to the green channel of the retinal image. It is based on the evaluation of the average grey level along lines of fixed length passing through the target pixel at different orientations. Two segmentation methods are considered. The first uses the basic line detector whose response is thresholded to obtain unsupervised pixel classification. As a further development, we employ two orthogonal line detectors along with the grey level of the target pixel to construct a feature vector for supervised classification using a support vector machine. The effectiveness of both methods is demonstrated through receiver operating characteristic analysis on two publicly available databases of color fundus images.

Associative memory design using support vector machines.

The relation existing between support vector machines (SVMs) and recurrent associative memories is investigated. The design of associative memories based on the generalized brain-state-in-a-box (GBSB) neural model is formulated as a set of independent classification tasks which can be efficiently solved by standard software packages for SVM learning. Some properties of the networks designed in this way are evidenced, like the fact that surprisingly they follow a generalized Hebb's law. The performance of the SVM approach is compared to existing methods with nonsymmetric connections, by some design examples.

Analog neural network for support vector machine learning.

An analog neural network for support vector machine learning is proposed, based on a partially dual formulation of the quadratic programming problem. It results in a simpler circuit implementation with respect to existing neural solutions for the same application. The effectiveness of the proposed network is shown through some computer simulations concerning benchmark problems.

Associative memory design for 256 gray-level images using a multilayer neural network.

A design procedure is presented for neural associative memories storing gray-scale images. It is an evolution of a previous work based on the decomposition of the image with 2L gray levels into L binary patterns, stored in L uncoupled neural networks. In this letter, an L-layer neural network is proposed with both intralayer and interlayer connections. The connections between different layers introduce interactions among all the neurons, increasing the recall performance with respect to the uncoupled case. In particular, the proposed network can store images with the commonly used number of 256 gray levels instead of 16, as in the previous approach.

Training Spatially Homogeneous Fully Recurrent Neural Networks in Eigenvalue Space.

A new design method for spatially-homogeneous, fully recurrent neural networks is presented. In our approach the eigenvalues of the synaptic matrix, rather than the weights, are learned from the examples. When the learning process is carried out, the connection weights are easily computed from the eigenvalues by inverse discrete Fourier transform. The adaptation is performed in the eigenvalue space in order to simply incorporate in the training algorithm the conditions for the uniqueness of the steady-state. As a consequence, the trained networks are insensitive to initial conditions. The method is illustrated by computer simulations concerning two specific feature extraction examples. Copyright 1996 Elsevier Science Ltd.