5 papers
Choi--Jamiołkowski-type isomorphisms for von Neumann algebras
Marcin Marciniak, Michał Cholewiak
The Choi--Jamiołkowski isomorphism identifies completely positive maps with bipartite states and underlies much of finite-dimensional quantum information theory. For systems with i…
Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking
Chandler Timm C. Doloriel, Habib Ullah, Kristian Hovde Liland +2
Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and u…
RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning
William Heyden, Habib Ullah, M. Salman Siddiqui +1
In Generalized Zero-Shot Learning (GZSL), we aim to recognize both seen and unseen categories using a model trained only on seen categories. In computer vision, this translates int…
Building Trustworthy AI: Transparent AI Systems via Large Language Models, Ontologies, and Logical Reasoning (TranspNet)
Fadi Al Machot, Martin Thomas Horsch, Habib Ullah
Growing concerns over the lack of transparency in AI, particularly in high-stakes fields like healthcare and finance, drive the need for explainable and trustworthy systems. While…
Symbolic-AI-Fusion Deep Learning (SAIF-DL): Encoding Knowledge into Training with Answer Set Programming Loss Penalties by a Novel Loss Function Approach
Fadi Al Machot, Martin Thomas Horsch, Habib Ullah
This paper presents a hybrid methodology that enhances the training process of deep learning (DL) models by embedding domain expert knowledge using ontologies and answer set progra…