JavaScript is disabled for your browser. Some features of this site may not work without it.
Mimar Sinan Fine Arts University Institutional Repository
DSpace@MSGSÜ digitally stores academic resources such as books, articles, dissertations, bulletins, reports, research data published directly or indirectly by Mimar Sinan Fine Arts University in international standarts, helps track the academic performance of the university, provides long term preservation for resources and makes publications available to Open Access in accordance with their copyright to increase the effect of publications.
Neural networks have become popular in many fields of science since they serve as promising, reliable and powerful tools. In this work, we study the effect of data augmentation on the predictive power of neural network ...
Recently, credit scoring problems have come into prominence depending on growing the number of applicants. As known from literature, the traditional techniques are not sufficient to model this kind of problems accurately. ...
In recent years, we have witnessed the rise of deep learning. Deep neural networks have proved their success in many areas. However, the optimization of these networks has become more difficult as neural networks going ...
Soydaner, Derya(Mimar Sinan Güzel Sanatlar Üniversitesi, Fen Bilimleri Enstitüsü, 2018)
Bu çalışmada büyük bir sinir ağının parametrelerini üretmek için daha küçük bir üst sinir ağı kullanan üst özkodlayıcılar önerilmiştir. Önerilen üst özkodlayıcı, bir özkodlayıcının bütün parametrelerini doğrusal bir sinir ...
We introduce the hyper autoencoder architecture where a secondary, hypernetwork is used to generate the weights of the encoder and decoder layers of the primary, actual autoencoder. The hyper autoencoder uses a one-layer ...
In recent years, artificial neural networks and their applications for large data sets have become a crucial part of scientific research. In this work, we implement the Multilayer Perceptron (MLP), which is a class of ...
Over the past years, convolutional neural networks (CNNs) have achieved remarkable success in deep learning.The performance of CNN-based models has caused major advances in a wide range of tasks from computer vision tonatural ...