Search Results for author:
Found 3 papers, 0 papers with code
Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning.
Enhancement attacks in biomedical machine learning
In the spirit of developing attacks to better understand trustworthiness, we developed two techniques to drastically enhance prediction performance of classifiers with minimal changes to features: 1) general enhancement of prediction performance, and 2) enhancement of a particular method over another.
Data-driven mapping between functional connectomes using optimal transport
Being able to map connectomes and derived results between different atlases without additional pre-processing is a crucial step in improving interpretation and generalization between studies that use different atlases.
