Oramas, Jose

7 publications

ICLR 2025 Bilinear MLPs Enable Weight-Based Mechanistic Interpretability Michael T Pearce, Thomas Dooms, Alice Rigg, Jose Oramas, Lee Sharkey

ICLR 2025 Improving Neural Network Accuracy by Concurrently Training with a Twin Network Benjamin Vandersmissen, Lucas Deckers, Jose Oramas

ECML-PKDD 2025 SVEBI: Towards the Interpretation and Explanation of Spiking Neural Networks Jasper De Laet, Hamed Behzadi-Khormouji, Lucas Deckers, José Oramas

ECML-PKDD 2025 Smooth InfoMax - Towards Easier Post-Hoc Interpretability Fabian Denoodt, Bart de Boer, José Oramas

TMLR 2024 The Trifecta: Three Simple Techniques for Training Deeper Forward-Forward Networks Thomas Dooms, Ing Jyh Tsang, Jose Oramas

WACV 2023 A Protocol for Evaluating Model Interpretation Methods from Visual Explanations Hamed Behzadi-Khormouji, José Oramas

ICLR 2019 Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks Jose Oramas, Kaili Wang, Tinne Tuytelaars