G
Gungor Polatkan
Researcher at LinkedIn
Publications - 29
Citations - 893
Gungor Polatkan is an academic researcher from LinkedIn. The author has contributed to research in topics: Gibbs sampling & Hidden Markov model. The author has an hindex of 10, co-authored 29 publications receiving 641 citations. Previous affiliations of Gungor Polatkan include Boğaziçi University & Microsoft.
Papers
More filters
Posted Content
An Attentive Survey of Attention Models
TL;DR: A taxonomy that groups existing techniques into coherent categories in attention models is proposed, and how attention has been used to improve the interpretability of neural networks is described.
Journal ArticleDOI
Deep Learning with Hierarchical Convolutional Factor Analysis
TL;DR: Unsupervised multilayered (“deep”) models are considered for imagery, represented using a hierarchical convolutional factor-analysis construction, with sparse factor loadings and scores.
Journal ArticleDOI
A Bayesian Nonparametric Approach to Image Super-Resolution
TL;DR: In this paper, the authors developed a new Bayesian nonparametric model for super-resolution which uses a beta-Bernoulli process to learn a set of recurring visual patterns, called dictionary elements, from the data.
Posted Content
A Bayesian Nonparametric Approach to Image Super-resolution
TL;DR: This paper develops a new Bayesian nonparametric model for super-resolution that uses a beta-Bernoulli process to learn a set of recurring visual patterns, called dictionary elements, from the data.
Proceedings ArticleDOI
Detection of forgery in paintings using supervised learning
TL;DR: It is demonstrated that supervised machine learning on features derived from hidden-Markov-tree-modeling of the paintings' wavelet coefficients has the potential to distinguish copies from originals in the new dataset.