no code implementations • 5 Jan 2023 • Ozan Ozyegen, Juyoung Wang, Mucahit Cevik
Despite the high performance of neural network-based time series forecasting methods, the inherent challenge in explaining their predictions has limited their applicability in certain application areas.
no code implementations • 1 Aug 2022 • Ozan Ozyegen, Nicholas Prayogo, Mucahit Cevik, Ayse Basar
The explanations are used to obtain insights into the clustering models.
no code implementations • 2 Sep 2021 • Hadi Jahanshahi, Ozan Ozyegen, Mucahit Cevik, Beste Bulut, Deniz Yigit, Fahrettin F. Gonen, Ayşe Başar
In our experiments, we investigate the generalizability of the trained models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the benefits of incorporating product titles in multiple languages.
no code implementations • 21 May 2021 • Ozan Ozyegen, Devika Kabe, Mucahit Cevik
The first method uses TF-IDF scores directly to highlight important parts of the text.
no code implementations • 18 Sep 2020 • Ozan Ozyegen, Igor Ilic, Mucahit Cevik
In this study, we propose two novel evaluation metrics for time series forecasting: Area Over the Perturbation Curve for Regression and Ablation Percentage Threshold.
BIG-bench Machine Learning Multivariate Time Series Forecasting +2
no code implementations • 16 Jun 2020 • Ozan Ozyegen, Sanaz Mohammadjafari, Karim El mokhtari, Mucahit Cevik, Jonathan Ethier, Ayse Basar
We compare deep learning-based prediction models including RadioUNET and four different variations of the UNET model for the power prediction task.