Şaban Dalaman

Şaban Dalaman
Istanbul Sehir University · Computer Science

MSc

About

4
Publications
4,891
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
0
Citations
Citations since 2017
4 Research Items
0 Citations
201720182019202020212022202301234
201720182019202020212022202301234
201720182019202020212022202301234
201720182019202020212022202301234
Learn about citations on ResearchGate
Introduction
Skills and Expertise
Machine Learning
Advanced Machine Learning
Neural Networks and Artificial Intelligence
Deep Learning
Statistical Learning
Backpropagation
Natural Language Processing
Capital Markets
Algorithmic Trading
quantum machine learning
Additional affiliations
February 2019 - September 2019
Istanbul Sehir University
Istanbul Sehir University
  • Computer Science
  • Istanbul, Turkey
Position
  • Lecturer
Education
September 2015 - June 2017
Istanbul Sehir University
Istanbul Sehir University
Field of study
  • Machine Learning

Publications

Publications (4)
ECE580-Evolving-Networks
Preprint
Full-text available
  • Oct 2018
Most of the networks in nature including social networks are highly dynamic. It is usually difficult to form a good picture of evolution in “time axis”. There are many models developed to study the properties and structure of networks. But mostly they are about static networks. There has been not much interest and study on dynamic networks or evolv...
Compositional Representations of Language Structures in MultiLingual Joint-Vector Space
Preprint
  • Oct 2018
After the recent developments in Artificial Neural Networks and deep learning techniques, representation learning has become the focus of many research interests. In the field of Natural Language Processing, representation learning techniques have gained many implementation advances and improved different tasks compared to any other method. One of...
MULTI-LINGUAL REPRESENTATION LEARNING USING JOINT-SPACE REPRESENTATIONS
Article
  • Oct 2018
In the field of Natural Language Processing, representation learning techniques have gained many implementation advances and improved different tasks compared to any other methods. One of the primary research topics in this area is to construct compositional representations of discrete language structures in multilingual joint-vector space. In this...
Fig 2. Example plots for total within-cluster sum of squares.
Figure 4. PCA1 and PCA2 plot for k-means clusters
Fig 5: Histogram of gene variances for combined set
Fig 10. Clustering coefficient for each node
+1 Fig 13: Power law fit for each samples network
Finding Correlations Of Common Gene Expressions Of Multiple Genetic Diseases By Using Microarray Data
Preprint
Full-text available
  • Oct 2018
The gene regulatory network (GRN) reveals the regulatory relationships among genes and can provide a systematic understanding of molecular mechanisms underlying biological processes. The idea studied here is to compare the traditional analysis of microarray gene expression profiles and network analysis of GRN inferred using gene expression data. Th...

Network

Projects

Projects (2)
Bilingual word embeddings and transfer learning
Project
creating bilingual word embeddings and using this joint vector space vectors in other NLP tasks
NLP applications using multi-lingual word representations and deep learning methods
Archived project
Distributed word representation ,known as word embedding, is a language modelling and feature representation technique for various natural language processing tasks. It is a low-dimensional vector space where each word is represented as a vector. By training multi-language corpora a joint representation space can be constructed such that semantically similar words from different languages will be adjacent to each other.