Search Results for author:
Found 5 papers, 2 papers with code
Pointwise Representational Similarity
Concretely, we show how PNKA can be leveraged to develop a deeper understanding of (a) the input examples that are likely to be misclassified, (b) the concepts encoded by (individual) neurons in a layer, and (c) the effects of fairness interventions on learned representations.
Measuring Representational Robustness of Neural Networks Through Shared Invariances
Our work offers a new view on robustness by using another reference NN to define the set of perturbations a given NN should be invariant to, thus generalizing the reliance on a reference ``human NN'' to any NN.
Mitigating Bias in Facial Analysis Systems by Incorporating Label Diversity
Hence, in this work, we introduce a novel learning method that combines both subjective human-based labels and objective annotations based on mathematical definitions of facial traits.
Do Invariances in Deep Neural Networks Align with Human Perception?
One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans.
Component Analysis for Visual Question Answering Architectures
Our major contribution is to identify core components for training VQA models so as to maximize their predictive performance.
