Search Results for author:
Found 5 papers, 1 papers with code
Contestable AI needs Computational Argumentation
AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable.
ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
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.
CAFE: Conflict-Aware Feature-wise Explanations
Feature attribution methods are widely used to explain neural models by determining the influence of individual input features on the models' outputs.
SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]
Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging.
GraspCaps: A Capsule Network Approach for Familiar 6DoF Object Grasping
The obtained dataset is then used to train the GraspCaps network.
