Yigit Oktar

Yigit Oktar
Izmir University of Economics

PhD

About

19
Publications
7,271
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
37
Citations
Citations since 2017
17 Research Items
37 Citations
2017201820192020202120222023024681012
2017201820192020202120222023024681012
2017201820192020202120222023024681012
2017201820192020202120222023024681012
Additional affiliations
May 2017 - October 2019
Izmir University Of Economics
Position
  • Research Assistant
April 2014 - June 2014
Digitoy Games
Position
  • Game programmer
Description
  • Full stack development of a Java browser game.
Education
September 2015 - August 2020
Izmir University of Economics
Field of study
  • Computer Engineering
September 2011 - June 2013
University of Pennsylvania
Field of study
  • Robotics
September 2006 - June 2011
University of Chicago
Field of study
  • Computer Science

Publications

Publications (19)
Article
Full-text available
In case of high dimensionality, a class of data clustering methods has been proposed as a solution that includes suitable subspace search to find inherent clusters. Sparsity-based clustering approaches include a twist in subspace approach as they incorporate a dimensionality expansion through the usage of an overcomplete dictionary representation....
Article
Full-text available
It has already been proven that under certain circumstances dictionary learning for sparse representations is equivalent to conventional k-means clustering. Through additional modifications on sparse representations, it is possible to generalize the notion of centroids to higher orders. In a related algorithm which is called k-flats, q-dimensional...
Article
Full-text available
Dictionary learning for sparse representations has been successful in many reconstruction tasks. Simplicial learning is an adaptation of dictionary learning, where subspaces become clipped and acquire arbitrary offsets, taking the form of simplices. Such adaptation is achieved through additional constraints on sparse codes. Furthermore, an evolutio...
Preprint
Full-text available
Graph isomorphism is an important problem as its worst-case time complexity is not yet fully understood. In this study, we try to draw parallels between a related optimization problem called point set registration. A graph can be represented as a point set in enough dimensions using a simplex embedding and sampling. Given two graphs, the isomorphis...
Article
Full-text available
In conventional machine learning applications, each data attribute is assumed to be orthogonal to others. Namely, every pair of dimension is orthogonal to each other and thus there is no distinction of in-between relations of dimensions. However, this is certainly not the case in real world signals which naturally originate from a spatio-temporal c...
Conference Paper
Dictionary learning for sparse representations is generative in nature, hence discriminative modifications are commonly observed for classification problems. Classical dictionary learning bears a fundamental problem of not being capable of distinguishing two different classes lying on the same subspace, that cannot be resolved by any discriminative...
Conference Paper
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As human visual system works in binocular, the collaboration of the eyes with the two brain lobes needs more investi...
Preprint
Full-text available
In conventional machine learning applications, each data attribute is assumed to be orthogonal to others. Namely, every pair of dimension is orthogonal to each other and thus there is no distinction of in-between relations of dimensions. However, this is certainly not the case in real world signals which naturally originate from a spatio-temporal c...
Preprint
Dictionary learning for sparse representations has been successful in many reconstruction tasks. Simplicial learning is an adaptation of dictionary learning, where subspaces become clipped and acquire arbitrary offsets, taking the form of simplices. Such adaptation is achieved through additional constraints on sparse codes. Furthermore, an evolutio...
Preprint
In standard Turing test, a machine has to prove its humanness to the judges. By successfully imitating a thinking entity such as a human, this machine then proves that it can also think. However, many objections are raised against the validity of this argument. Such objections claim that Turing test is not a tool to demonstrate existence of general...
Preprint
Full-text available
In standard Turing test, a machine has to prove its humanness to the judges. By successfully imitating a thinking entity such as a human, this machine then proves that it can also think. However, many objections are raised against the validity of this argument. Such objections claim that Turing test is not a tool to demonstrate existence of general...
Technical Report
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As human visual system works in binocular, the collaboration of the eyes with the two brain lobes needs more investi...
Preprint
Full-text available
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As human visual system works in binocular, the collaboration of the eyes with the two brain lobes needs more investi...
Data
A concise presentation for the concept of k-polytopes
Article
Full-text available
Integration of intelligent systems in fashion and design related field is a relatively new concept. The aim of this research was to evaluate the performance of an intelligent fashion styling recommendation system for non-standard female body shapes. As a recommender strategy, the intelligent fashion styling system employs a two-stage genetic search...
Technical Report
Full-text available
PointCrust is a WebGL tool, based on three.js library, that converts a point cloud dataset to a triangle mesh structure. Berger et al. present a nice review on state of the art methods for surface reconstruction from point clouds. There are web tools for point cloud to mesh approximation such as MeshLab, however there is no dedicated tool for this...
Article
Full-text available
Machine learning usage in the neurosciences has been explosively increased for the past three years. Besides strengths and also the inherent misusage of machine learning in neurosciences, the results obtained from these studies suggest that machine learning methods may extensively be used for the clinical diagnosis and for the investigation of diff...

Network

Cited By

Projects

Projects (2)
Project
Graph and subgraph isomorphism problems are tightly related to P vs. NP problem. This project's objective is to investigate this problem through high dimensional geometric representations of graphs.
Project
An extension of dictionary learning to learn a union of simplices, instead of learning a union of subspaces.