Search Results for author:
Found 2 papers, 0 papers with code
Validation and generalization of pixel-wise relevance in convolutional neural networks trained for face classification
To be interpretable and useful to humans, such a method should convey a model's learned classification strategy in a way that is robust to random initializations or spurious correlations in input data.
The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariance
Because training artificial neural networks from scratch is similar to showing novel objects to humans, we seek to understand the factors influencing the tolerance of CNNs to spatial transformations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
