Derin Öğrenme

Date

2018-11-01

Author

Yarman Vural, Fatoş Tunay
Cinbiş, Ramazan Gökberk
Kalkan, Sinan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

174
views

0
downloads

URI

http://www.buzdagiyayinevi.com/derin-ogrenme/
https://hdl.handle.net/11511/70286

Collections

Department of Computer Engineering, Book / Book chapter

Suggestions

OpenMETU
Core

Novel Optimization Models to Generalize Deep Metric Learning Gürbüz, Yeti Ziya; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-8-24) Deep metric learning (DML) aims to fit a parametric embedding function to data of semantic information (e.g. images) so that l2-distance between embedded samples is low whenever they share similar semantic entities. An embedding function of such behavior is attained by minimizing empirical expected pairwise loss that penalizes inter-/intra-class proximity violations in embedding space. Proxy-based methods which use a learnable embedding vector per class in their loss formulation are state-of-the-art. We fir...
Derin Sinir Ağları Ile Videolarda Nesne Algılama Akbaş, Emre; Kalkan, Sinan(2021-04-01) Nesne tespiti, verilen bir görüntüde yer alan nesnelerin ve görüntüdeki konumlarının belirlenmesi problemidir. Modern nesne tespiti yöntemleri, problemi, ?arama? ve ?tanıma? olarak adlandırabileceğimiz iki aşamada çözerler. Arama aşamasında sınıftan bağımsız olarak nesne adayları belirlenir, tanıma aşamasında ise bu adayların sınıfları kestirilir. Tamamlamakta olduğumuz projemizin iki temel odağı vardı ve katkılarımız temel olarak bu iki odakta toplandı: (1) Nesne tespitinde bağlam: Görüntülerde ve vi...
Social media image classification using deep convolutional neural networks Akpak, Çağrı Utku; Alpaslan, Ferda Nur; Department of Computer Engineering (2017) Increasing popularity of social media platforms has led to an increase in the number of unclassified images. Given the complexity of images uploaded to these platforms and the number of classes available, it is clear that traditional image classification methods are not suitable for this kind of classification. Previous research on this topic primarily focuses on Deep Neural Networks to overcome the limitations of traditional methods. In these studies, researchers either limited the scope of their dataset; ...
Modeling of carbon dioxide sequestration in a deep saline aquifer Başbuğ, Başar; Gümrah, Fevzi; Department of Petroleum and Natural Gas Engineering (2005) CO2 is one of the hazardous greenhouse gases causing significant changes in the environment. The sequestering CO2 in a suitable geological medium can be a feasible method to avoid the negative effects of CO2 emissions in the atmosphere. CO2 sequestration is the capture of, separation, and long-term storage of CO2 in underground geological environments. A case study was simulated regarding the CO2 sequestration in a deep saline aquifer. The compositional numerical model (GEM) of the CMG software was used to ...
Multivariate Forecasting of Global Horizontal Irradiation Using Deep Learning Algorithms Vakitbilir, Nuray; Direkoğlu, Cem; Sustainable Environment and Energy Systems (2021-2-11) Increasing photovoltaic (PV) panel instalments jeopardise the electrical grid frequency, especially in island countries, such as Cyprus. For a continuous growth in the PV instalments in Northern Cyprus as well as minimal usage of conventional energy sources in power generation, it is of utter importance for a grid manager to possess information on the energy production of PV panels, hence knowledge on received radiation, i.e. Global Horizontal Irradiation (GHI). Therefore, the prediction of GHI plays an ess...

Citation Formats

F. T. Yarman Vural, R. G. Cinbiş, and S. Kalkan, Derin Öğrenme. 2018.