2 papers
cs.CV2021
Gradient-Based Interpretability Methods and Binarized Neural Networks
Amy Widdicombe, Simon J. Julier
Binarized Neural Networks (BNNs) have the potential to revolutionize the way that deep learning is carried out in edge computing platforms. However, the effectiveness of interpreta…
cs.CV2019
NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning
Moustafa Alzantot, Amy Widdicombe, Simon Julier +1
Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these mod…