3 citations · 4 across the 7 of their papers we have counts for
3 papers · 1 filter
Targeted Activation Penalties Help CNNs Ignore Spurious Signals
Dekai Zhang, Matthew Williams, Francesca Toni
Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional…
ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
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. While earl…
Hidden Conflicts in Neural Networks and Their Implications for Explainability
Adam Dejl, Dekai Zhang, Hamed Ayoobi +2
Artificial Neural Networks (ANNs) often represent conflicts between features, arising naturally during training as the network learns to integrate diverse and potentially disagreei…