Continuous word recognition using neural networks

Dağıtan, Ümit


Deep learning-based image transmission through a multi-modefiber
Kürekçi, Şahin; Odabaş, Ekrem; Temur, Tarık; Afshari, Gilda; Yüce, Emre (null; 2020-04-09)
Image transmission through a multi-mode fiber is a difficult task given the complex interference of light through the fiber that leads to random speckle patterns at the distal end of the fiber. With traditional methods and techniques, it is impractical to reconstruct a high-resolution input image by using the information obtained from the intensity of the corresponding output speckle alone. In this work, we train three Convolutional Neural Networks (CNNs) with input-output couples of a multi-mode fiber and ...
Continuous-time Nonlinear Estimation Filters Using UKF-aided Gaussian Sum Representations
Gokce, Murat; Kuzuoğlu, Mustafa (2013-07-12)
An approximate nonlinear estimation method for continuous-time systems with discrete-time measurements is developed. The approach evaluates the Gaussian sum approximation of the a priori probability density function (pdf) by solving the Fokker-Planck equation numerically. Approximate evaluation of the a posteriori pdf is achieved by using Gaussian sums, a priori pdf and measurements in Bayes rule. Mean and covariance values of Gaussians are chosen by the help of an Unscented Kalman Filter (UKF), with respec...
Continuous-time nonlinear estimation filters using UKF-aided gaussian sum representations
Gökçe, Murat; Kuzuoğlu, Mustafa; Department of Electrical and Electronics Engineering (2014)
A nonlinear filtering method is developed for continuous-time nonlinear systems with observations/measurements carried out in discrete-time by means of UKFaided Gaussian sum representations. The time evolution of the probability density function (pdf) of the state variables (or the a priori pdf) is approximated by solving the Fokker-Planck equation numerically using Euler’s method. At every Euler step, the values of the a priori pdf are evaluated at deterministic sample points. These values are used with Ga...
Continuous learning processes in creating the public realm
Ataoev, A. (Thomas Telford Ltd., 2007-09-01)
This paper presents a three-year long participatory action research (PAR) project conducted in collaboration with government officials, researchers, social workers and 400 street children in six Turkish metropolitan cities. By utilising the experiences of this project, it is argued that inclusive planning of public space requires a 'process' approach that can stimulate those involved to a more liberating state. The PAR methodologies can provide the means to conduct planning in a process of participation and...
Continuous synthesis of graphite with tunable interlayer distance
ÇAKMAK, GÜLHAN; Öztürk, Tayfur (2019-06-01)
A study was carried out to produce graphite with controlled interlayer distance synthesized from methane using hydrogen as modifying agent. The synthesis was carried out in radio frequency (r.f.) thermal plasma where the methane-to-hydrogen ratio varied systematically over a wide range. The synthesized materials were investigated in terms of structure, morphology and the interlayer distance. It is found that there is a critical fraction of hydrogen, around half of that of methane flow rate, up to which it i...
Citation Formats
Ü. Dağıtan, “Continuous word recognition using neural networks,” Middle East Technical University, 1989.