no code implementations • 12 Dec 2023 • Andac Demir, Francis Prael III, Bulent Kiziltan
We explore the underlying topologies and patterns in molecular structures by applying Vietoris-Rips persistent homology across varying scales and parameters such as atomic weight, partial charge, bond type, and chirality.
no code implementations • 17 Nov 2023 • Andac Demir, Bulent Kiziltan
In this study, we present a novel molecular fingerprint generation method based on multiparameter persistent homology.
no code implementations • 24 Apr 2023 • Andac Demir, Elie Massaad, Bulent Kiziltan
To tackle this problem, we introduce a novel loss function, namely Topology-Aware Focal Loss (TAFL), that incorporates the conventional Focal Loss with a topological constraint term based on the Wasserstein distance between the ground truth and predicted segmentation masks' persistence diagrams.
no code implementations • 8 Dec 2022 • Andac Demir, Iya Khalil, Bulent Kiziltan
One of the main challenges in electroencephalogram (EEG) based brain-computer interface (BCI) systems is learning the subject/session invariant features to classify cognitive activities within an end-to-end discriminative setting.
no code implementations • 7 Nov 2022 • Andac Demir, Baris Coskunuzer, Ignacio Segovia-Dominguez, Yuzhou Chen, Yulia Gel, Bulent Kiziltan
In computer-aided drug discovery (CADD), virtual screening (VS) is used for identifying the drug candidates that are most likely to bind to a molecular target in a large library of compounds.
no code implementations • 16 Jun 2021 • Andac Demir, Toshiaki Koike-Akino, Ye Wang, Masaki Haruna, Deniz Erdogmus
Convolutional neural networks (CNN) have been frequently used to extract subject-invariant features from electroencephalogram (EEG) for classification tasks.
no code implementations • 17 Feb 2021 • Ozan Ozdenizci, Safaa Eldeeb, Andac Demir, Deniz Erdogmus, Murat Akcakaya
Multiple cortical brain regions are known to be responsible for sensory recognition, perception and motor execution during sensorimotor processing.
no code implementations • 2 Jul 2020 • Andac Demir, Toshiaki Koike-Akino, Ye Wang, Deniz Erdogmus
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning.