Towards enhancing the reproducibility of deep learning bugs: an empirical study
Context Deep learning has achieved remarkable progress in various domains. However,
like any software system, deep learning systems contain bugs, some of which can have …
like any software system, deep learning systems contain bugs, some of which can have …
Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification
Deep Neural Networks (DNN) have found numerous applications in various domains,
including fraud detection, medical diagnosis, facial recognition, and autonomous driving …
including fraud detection, medical diagnosis, facial recognition, and autonomous driving …
Predicting the Reliability of an Image Classifier under Image Distortion
In image classification tasks, deep learning models are vulnerable to image distortions ie
their accuracy significantly drops if the input images are distorted. An image-classifier is …
their accuracy significantly drops if the input images are distorted. An image-classifier is …