Search Results for author:
Found 5 papers, 2 papers with code
The need to implement FAIR principles in biomolecular simulations
This letter illustrates the opinion of the molecular dynamics (MD) community on the need to adopt a new FAIR paradigm for the use of molecular simulations.
Explanation is All You Need in Distillation: Mitigating Bias and Shortcut Learning
We found that it is possible to train a neural network with explanation (e. g by Layer Relevance Propagation, LRP) distillation only, and that the technique leads to high resistance to shortcut learning, surpassing group-invariant learning, explanation background minimization, and alternative distillation techniques.
Faster ISNet for Background Bias Mitigation on Deep Neural Networks
Representing a potentially massive training speed improvement over ISNet, the proposed architectures introduce LRP optimization into a gamut of applications that the original model cannot feasibly handle.
Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias.
Conceptron: a probabilistic deep one-class classification method
One-class learning through deep architectures is a particularly challenging task; in this scenario the crasis of kernel methods and deep networks can represent a viable strategy to empower already effective methods.
