Search Results for author: Alper T. Erdogan

Found 7 papers, 5 papers with code

A Bayesian Perspective for Determinant Minimization Based Robust Structured Matrix Factorizatio

no code implementations16 Feb 2023 Gokcan Tatli, Alper T. Erdogan

We introduce a Bayesian perspective for the structured matrix factorization problem.

Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation

1 code implementation9 Oct 2022 Bariscan Bozkurt, Ates Isfendiyaroglu, Cengiz Pehlevan, Alper T. Erdogan

Here, we relax this limitation and propose a biologically plausible neural network that extracts correlated latent sources by exploiting information about their domains.

Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources

2 code implementations27 Sep 2022 Bariscan Bozkurt, Cengiz Pehlevan, Alper T. Erdogan

Previous work on biologically-plausible BSS algorithms assumed that observed signals are linear mixtures of statistically independent or uncorrelated sources, limiting the domain of applicability of these algorithms.

Self-Supervised Learning with an Information Maximization Criterion

1 code implementation16 Sep 2022 Serdar Ozsoy, Shadi Hamdan, Sercan Ö. Arik, Deniz Yuret, Alper T. Erdogan

In this article, we argue that a straightforward application of information maximization among alternative latent representations of the same input naturally solves the collapse problem and achieves competitive empirical results.

Self-Supervised Learning

On Identifiable Polytope Characterization for Polytopic Matrix Factorization

1 code implementation25 Apr 2022 Bariscan Bozkurt, Alper T. Erdogan

We show how this problem can be efficiently solved by using a graph automorphism algorithm.

Polytopic Matrix Factorization: Determinant Maximization Based Criterion and Identifiability

no code implementations19 Feb 2022 Gokcan Tatli, Alper T. Erdogan

In this sense, the article considers a semi-structured data model, in which the input matrix is modeled as the product of a full column rank matrix and a matrix containing samples from a polytope as its column vectors.

Blind Bounded Source Separation Using Neural Networks with Local Learning Rules

1 code implementation11 Apr 2020 Alper T. Erdogan, Cengiz Pehlevan

An important problem encountered by both natural and engineered signal processing systems is blind source separation.

Cannot find the paper you are looking for? You can Submit a new open access paper.