Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers

Autor: Sevim, Nurullah, Özyedek, Ege Ozan, Şahinuç, Furkan, Koç, Aykut

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other areas. Althou

Externí odkaz: http://arxiv.org/abs/2209.12816

Joint Time-Vertex Fractional Fourier Transform

Autor: Alikaşifoğlu, Tuna, Kartal, Bünyamin, Özgünay, Eray, Koç, Aykut

Graph signal processing (GSP) facilitates the analysis of high-dimensional data on non-Euclidean domains by utilizing graph signals defined on graph vertices. In addition to static data, each vertex can provide continuous time-series signals, transfo

Externí odkaz: http://arxiv.org/abs/2203.07655

Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance

Autor: Yilmaz, Selim F., Kaynak, E. Batuhan, Koç, Aykut, Dibeklioğlu, Hamdi, Kozat, Suleyman S.

We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics and social sciences. In particular, we introduce a sentiment analysis framework in

Externí odkaz: http://arxiv.org/abs/2008.11573

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Deep Iterative Reconstruction for Phase Retrieval

Autor: Işıl, Çağatay, Oktem, Figen S., Koç, Aykut

Publikováno v: \c{C}a\u{g}atay I\c{s}{\i}l, Figen S. Oktem, and Aykut Ko\c{c}, "Deep iterative reconstruction for phase retrieval," Appl. Opt. 58, 5422-5431 (2019)

Classical phase retrieval problem is the recovery of a constrained image from the magnitude of its Fourier transform. Although there are several well-known phase retrieval algorithms including the hybrid input-output (HIO) method, the reconstruction

Externí odkaz: http://arxiv.org/abs/1904.11301