Yılmaz, Cansen

Profile Picture
Name Variants
Yılmaz,C.
C.,Yılmaz
C.,Yilmaz
Cansen, Yılmaz
Cansen, Yilmaz
Yılmaz, Cansen
Y.,Cansen
C., Yilmaz
Y., Cansen
Yilmaz,C.
Yilmaz, Cansen
Caglayan,C.
Çağlayan,C.
Job Title
Araştırma Görevlisi
Email Address
cansen.caglayan@atilim.edu.tr
Main Affiliation
Computer Engineering
Status
Former Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID

Sustainable Development Goals Report Points

SDG data could not be loaded because of an error. Please refresh the page or try again later.
Scholarly Output

2

Articles

0

Citation Count

6

Supervised Theses

0

Filters

2019 - 201912020 - 20211
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 5
    Topic-Controlled Text Generation
    (Institute of Electrical and Electronics Engineers Inc., 2021) Çağlayan,C.; Karakaya,M.; Computer Engineering
    Today, the text generation subject in the field of Natural Language Processing (NLP) has gained a lot of importance. In particular, the quality of the text generated with the emergence of new transformer-based models has reached high levels. In this way, controllable text generation has become an important research area. There are various methods applied for controllable text generation, but since these methods are mostly applied on Recurrent Neural Network (RNN) based encoder decoder models, which were used frequently, studies using transformer-based models are few. Transformer-based models are very successful in long sequences thanks to their parallel working ability. This study aimed to generate Turkish reviews on the desired topics by using a transformer-based language model. We used the method of adding the topic information to the sequential input. We concatenated input token embedding and topic embedding (control) at each time step during the training. As a result, we were able to create Turkish reviews on the specified topics. © 2021 IEEE
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 5
    Comparison of the Code-Based or Tool-Based Teaching of the Machine Learning Algorithm for the First-Time Learners
    (Institute of Electrical and Electronics Engineers Inc., 2019) Caglayan,C.; Computer Engineering
    In this study, teaching machine learning algorithms by using a software tool or with the code based methods were compared according to level of interest for the subject and perception of self-knowledge of the first time learners. Eleven participants were first year students from computer, software and information systems engineering departments who completed the C programming language course at the university. Participants were divided into two groups. Both groups were given basic theoretical knowledge about machine learning and one of the easiest algorithms to implement k-Nearest Neighbors (kNN) algorithm at the same level. The kNN algorithm, was explained to a group with the C programming language code implementation, and the other group with using a software tool Orange3 which has designed for implementing machine learning algorithms easily. Two questionnaires were applied to both groups. One was applied to measure their level of knowledge of programming and basic knowledge of machine learning. Other one was applied to measure their thoughts about knowledge and level of interest in the subject after the lecture. The aim of this study is to investigate whether we can improve the level of interest of students about machine learning by using code based or tool based environment for the first time learners and find the best teaching environment for them at the beginning. © 2019 IEEE.