Burcu Erkmen

Learn More
In this brief, conic section function neural network (CSFNN) circuitry was designed for offline signature recognition. CSFNN is a unified framework for multilayer perceptron (MLP) and radial basis function (RBF) networks to make simultaneous use of advantages of both. The CSFNN circuitry architecture was developed using a mixed mode circuit implementation.(More)
Natural organs are spatially heterogeneous, both in material composition and in the cell types within. Engineered tissues, in contrast, remain challenging to create, especially if the goal is to spatially position multiple cell types in a heterogeneous pattern in three dimensions (3D). Here, we describe a simple, inexpensive , yet extremely precise method(More)
In this paper, a Conic Section Function Neural Network (CSFNN) based system for signature recognition problem is developed. The purpose of this work is to optimize CSFNN parameters for signature recognition problem to be applied to the VLSI Neural Network (NN) chip. Signature database is constructed after some preprocessing techniques are applied on(More)
—This work presents efficient constrained optimization methods for sizing of a differential amplifier with current mirror load. The aim is to minimize MOS transistor area using three evolutionary algorithms, differential evolution, artificial bee colony algorithm and harmony search. Simulation results demonstrate that proposed methods not only meets design(More)
In this paper, decision boundaries of conic section function neural network (CSFNN) neuron obtained with current mode analog circuitry are presented. The designed circuit computes the radial basis function (RBF) and multilayer perceptron (MLP) propagation rules on a single hardware to form a CSFNN neuron. Decision boundaries, hyper plane (for MLP) and hyper(More)
In this paper, a circuit system of General Purposed Conic Section Function Neural Network is presented. The feed-forward analog computational cells have been designed by using the current mode approach. The network is trained in a chip-in-the-loop fashion with a host computer implementing the training algorithm. The network inputs and the feed-forward(More)
In this work, multilayer perceptron (MLP) has been trained by differential evolution algorithm (DEA) and the performance of the neural network has been analyzed by using high-dimensional and non-linear signature recognition data base. DEA, which doesn't depend on the initial weight values and doesn't stick in local minimums, carries out the global(More)
Linear Frequency Modulated Continuous Waveform is generally used in Low Probability of Intercept radars. In studies to intercept this waveform with Wigner-Hough Transform based methods at low SNR (-8dB and below) values it is an important design criteria to obtain the resulting performance with less computation density. The decrease in computation density(More)