Melis OZYILDIRIM

Melis OZYILDIRIM
Cukurova University | CU · Department of Computer Engineering

PhD

About

20
Publications
3,576
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
201
Citations
Additional affiliations
January 2016 - present
Cukurova University
Position
  • Asst. Prof. Dr.
November 2012 - present
Adana Science and Technology University
Position
  • Research Assistant
Education
September 2010 - June 2012
Cukurova University
Field of study
  • Computer Engineering
September 2006 - June 2010
Cukurova University
Field of study
  • Computer Engineering

Publications

Publications (20)
Preprint
Full-text available
Reinforcement learning (RL) applications, where an agent can simply learn optimal behaviors by interacting with the environment, are quickly gaining tremendous success in a wide variety of applications from controlling simple pendulums to complex data centers. However, setting the right hyperparameters can have a huge impact on the deployed solutio...
Article
Incorporating higher-order optimization functions, such as Levenberg–Marquardt (LM) have revealed better generalizable solutions for deep learning problems. However, these higher-order optimization functions suffer from very large processing time and training complexity especially as training data sets become large, such as in multi-view classifica...
Article
Full-text available
Up to date technological implementations of deep convolutional neural networks are at the forefront of many issues, such as autonomous device control, effective image and pattern recognition solutions. Deep neural networks generally utilize a hybrid topology of a feature extractor containing convolutional layers followed by a fully connected classi...
Preprint
With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention. Several implementations favor the use of Conjugate Gradient (CG) and Stochastic Gradient Descent (SGD) as being practical and elegant solutions to achieve quick convergence, howev...
Chapter
Technological improvements lead big data producing, processing and storing systems. These systems must contain extraordinary capabilities to overcome complexity of the big data. Therefore, the methodologies utilized for data analysis have been evolved due to the increase in importance of extracting information from big data. Healthcare systems are...
Article
Convolutional neural networks with strong representation ability of deep structures have ever increasing popularity in many research areas. The main difference of Convolutional Neural Networks with respect to existing similar artificial neural networks is the inclusion of the convolutional part. This inclusion directly increases the performance of...
Patent
Full-text available
The invention relates to the determination of the level of coal dusts deposits in underground mine galleries, it is possible to quickly determine the rates of limestone powder / coal dust in the dust samples taken from the mine and play an important role in taking the necessary precautions to prevent the coal dust explosion by directing the user, i...
Article
Full-text available
In this study, the results obtained from the experiments with the camera image-based system developed for determining the amount of stone dust to determine the explosion limits of the coal dusts accumulated during the underground production, transport and storage works and to prevent explosion were compared with the results of the stone dust-coal d...
Article
Extreme Learning Machine (ELM) method is proposed for single hidden layer feed-forward networks (SLFNs). The ELM employs feed-forward neural network architecture and works with randomly determined input weights. In this respect, ELM depends on the principle that enables to determine weights and biases in the network. In the first phase of ELM which...
Article
Full-text available
In a general regression neural network (GRNN), the number of neurons in the pattern layer is proportional to the number of training samples in the dataset. The use of a GRNN in applications that have relatively large datasets becomes troublesome due to the architecture and speed required. The great number of neurons in the pattern layer requires a...
Article
Full-text available
According to some estimates of World Health Organization, in 2014, more than 1.9 billion adults were overweight. About 13% of the world’s adult population were obese. 39% of adults were overweight. The worldwide prevalence of obesity more than doubled between 1980 and 2014. Nowadays, mobile applications recording food intake of people become popula...
Article
Full-text available
Displaying useful and meaningful information from 3D data is known as volume rendering. Ray casting is one of the most frequently used direct volume rendering methods. It consists of data preparation, sampling, classification, compositing, and shading steps. Normal values are needed for efficient shading. However, 3D volumetric data are discrete an...
Article
Generalized classifier neural network introduced as a kind of radial basis function neural network, uses gradient descent based optimized smoothing parameter value to provide efficient classification. However, optimization consumes quite a long time and may cause a drawback. In this work, one pass learning for generalized classifier neural network...
Article
Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning a...
Article
In this work a new radial basis function based classification neural network named as generalized classifier neural network, is proposed. The proposed generalized classifier neural network has five layers, unlike other radial basis function based neural networks such as generalized regression neural network and probabilistic neural network. They ar...

Network

Cited By