Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1941

Browse

Browsing Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu by Institution Author "Kırbız, Serap"

Filter results by typing the first few letters
Now showing 1 - 5 of 5
  • Thumbnail Image
    Article
    A Bayesian Allocation Model Based Approach To Mixed Membership Stochastic Blockmodels
    (Taylor and Francis Ltd., 2022) Kırbız, Serap; Hızlı, Çağlar
    Although detecting communities in networks has attracted considerable recent attention, estimating the number of communities is still an open problem. In this paper, we propose a model, which replicates the generative process of the mixed-membership stochastic block model (MMSB) within the generic allocation framework of Bayesian allocation model (BAM) and BAM-MMSB. In contrast to traditional blockmodels, BAM-MMSB considers the observations as Poisson counts generated by a base Poisson process and marks according to the generative process of MMSB. Moreover, the optimal number of communities for BAM-MMSB is estimated by computing the variational approximations of the marginal likelihood for each model order. Experiments on synthetic and real data sets show that the proposed approach promises a generalized model selection solution that can choose not only the model size but also the most appropriate decomposition.
  • Thumbnail Image
    Article
    Citation - WoS: 22
    Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
    (Institute of Electrical and Electronics Engineers (IEEE), 2019) Kırbız, Serap; Karamatlı, Ertuğ; Cemgil, Ali Taylan
    In this letter, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a sound mixture. After training the model on mixtures, we obtain a generative model for each source class and demonstrate our method on one-second mixtures of utterances of digits from 0 to 9. We show that the separation performance obtained by source class supervision is as good as the performance obtained by source signal supervision.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 1
    Citation - Scopus: 1
    İlişkisel Veri Ayrıştırılmasında Model Seçimi
    (IEEE, 2019) Kırbız, Serap; Cemgil, Taylan; Hızlı, Çağlar
    Abstract—As a fundamental problem in relational data analysis, model selection for relational data factorization is still an open problem. In our work, we propose to estimate model order for mixed membership blockmodels (MMSB) within the generic allocation framework of Bayesian allocation model (BAM). We describe how relational data is represented as Poisson counts of the allocation model, and demonstrate our results both on synthetic and real-world data sets. We believe that the generic allocation perspective promises a generalized model selection solution where we do not only select the model order, but also choose the most appropriate factorization.
  • Thumbnail Image
    Conference Object
    Joint Source Separation and Classification Using Variational Autoencoders
    (IEEE, 2020) Karamatlı, Ertuğ; Kırbız, Serap; Hızlı, Çağlar
    In this paper, we propose a novel multi-task variational auto encoder (VAE) based approach for joint source separation and classification. The network uses a probabilistic encoder for each sources to map the input data to latent space. The latent representation is then used by a probabilistic decoder for the two tasks: source separation and source classification. Throughout a variety of experiments performed on various image and audio datasets, source separation performance of our method is as good as the method that performs source separation under source class supervision. In addition, the proposed method does not require the class labels and can predict the labels.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 3
    Citation - Scopus: 5
    Negatif Olmayan Gürültü Giderici Değişimli Oto-kodlayıcılar Kullanarak Tek Kanaldan Kaynak Ayrıştırma için Zayıf Etiket Denetimi
    (IEEE, 2019) Karamatlı, Ertuğ; Cemgil, Ali Taylan; Kırbız, Serap
    Derin öğrenme modelleri, büyük miktarda etiketlenmiş veri bulunduğunda kaynak ayrıştırmada çok başarılı olmaktadır. Bununla birlikte, dikkatlice etiketlenmiş veri kümelerine erişim her zaman mümkün olmamaktadır. Bu bildiride, kısa konuşma karışımlarını ayrıştırmayı öğrenmek için kaynak işaretlerini değil de sadece sınıf bilgisini kullanan zayıf bir denetim önerilmektedir. Negatif olmayan bir modeldeki her bir sınıfla degişimsel bir otomatik kodlayıcıyı (VAE) ilişkilendirilmektedir. Derin evrisimsel VAE’lerin, herhangi bir kaynak sinyaline ihtiyaç duymadan, bir ses karı¸sımındaki karmasık isaretleri kestirmek için önsel bir model sundugu gösterilmektedir. Ayrıstırma sonuçlarının kaynak isaret denetimiyle esit düzeyde oldugu gösterilmektedir.