no code implementations • 26 Nov 2023 • Hamed Ayoobi, Nico Potyka, Francesca Toni
We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e. g. in ProtoPNet.
no code implementations • 31 Oct 2023 • Adam Dejl, Hamed Ayoobi, Matthew Williams, Francesca Toni
Feature attribution methods are widely used to explain neural models by determining the influence of individual input features on the models' outputs.
1 code implementation • 23 Jan 2023 • Hamed Ayoobi, Nico Potyka, Francesca Toni
Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging.
no code implementations • 7 Oct 2022 • Tomas van der Velde, Hamed Ayoobi, Hamidreza Kasaei
The obtained dataset is then used to train the GraspCaps network.