Add to ORKGInternational audienceDeep learning systems recently achieved unprecedented success in various industries. However, DNNs still exhibit some erroneous behaviors, which lead to catastrophic results. As a result, more data should be collected to cover more corner cases. On the other hand, a massive amount of data consumes more human annotators (oracle), which increases the labeling budget and time. We propose an effective test prioritization technique, called DeepAbstraction to prioritize the more likely error-exposing instances among the entire unlabeled test dataset. The ultimate goal of our framework is to reduce the labeling cost and select the potential corner cases earlier before production. Different from existing work, DeepAbstraction ...
Thesis (Ph.D.)--University of Washington, 2020Machine learning using deep neural networks -- also ca...
Test Case Prioritization (TCP) has gained wide spread acceptance as it often results in good quality...
During minibatch gradient-based optimization, the contribution of observations to the updating of th...
International audienceDeep learning systems recently achieved unprecedented success in various indus...
Test Input Prioritizers (TIP) for Deep Neural Networks (DNN) are an important technique to handle th...
Deep learning plays a more and more important role in our daily life due to its competitive performa...
Testing deep learning-based systems is crucial but challenging due to the required time and labor fo...
Assessing the quality of Deep Learning (DL) systems is crucial, as they are increasingly adopted in ...
Deep learning is increasingly applied to safety-critical application domains such as autonomous cars...
peer reviewedSimilar to traditional software that is constantly under evolution, deep neural network...
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoint...
Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real wor...
Deep neural networks (DNNs) have achieved near-human level accuracy on many datasets across differen...
Deep neural networks (DNNs) have a wide range of applications, and software employing them must be t...
This paper summarizes eight design requirements for DNN testing criteria, taking into account distri...
Thesis (Ph.D.)--University of Washington, 2020Machine learning using deep neural networks -- also ca...
Test Case Prioritization (TCP) has gained wide spread acceptance as it often results in good quality...
During minibatch gradient-based optimization, the contribution of observations to the updating of th...
International audienceDeep learning systems recently achieved unprecedented success in various indus...
Test Input Prioritizers (TIP) for Deep Neural Networks (DNN) are an important technique to handle th...
Deep learning plays a more and more important role in our daily life due to its competitive performa...
Testing deep learning-based systems is crucial but challenging due to the required time and labor fo...
Assessing the quality of Deep Learning (DL) systems is crucial, as they are increasingly adopted in ...
Deep learning is increasingly applied to safety-critical application domains such as autonomous cars...
peer reviewedSimilar to traditional software that is constantly under evolution, deep neural network...
This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoint...
Deep Neural Networks (DNN) are typically tested for accuracy relying on a set of unlabelled real wor...
Deep neural networks (DNNs) have achieved near-human level accuracy on many datasets across differen...
Deep neural networks (DNNs) have a wide range of applications, and software employing them must be t...
This paper summarizes eight design requirements for DNN testing criteria, taking into account distri...
Thesis (Ph.D.)--University of Washington, 2020Machine learning using deep neural networks -- also ca...
Test Case Prioritization (TCP) has gained wide spread acceptance as it often results in good quality...
During minibatch gradient-based optimization, the contribution of observations to the updating of th...