Add to ORKGRecent deep learning (DL) applications are mostly built on top of DL libraries. The quality assurance of these libraries is critical to the dependable deployment of DL applications. A few techniques have thereby been proposed to test DL libraries by generating DL models as test inputs. Then these techniques feed those DL models to DL libraries for making inferences, in order to exercise DL libraries modules related to a DL model's execution. However, the test effectiveness of these techniques is constrained by the diversity of generated DL models. Our investigation finds that these techniques can cover at most 11.7% of layer pairs (i.e., call sequence between two layer APIs) and 55.8% of layer parameters (e.g., "padding" in Conv2D). As a re...
The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their gen...
An underlying mechanism for successful deep learning (DL) with a limited deep architecture and datas...
It is difficult for humans to distinguish the true and false of rumors, but current deep learning mo...
For the last decade, deep learning (DL) has emerged as a new effective machine learning approach tha...
Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adop...
Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate...
DL frameworks are the basis of constructing all DL programs and models, and thus their bugs could le...
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A si...
A growing body of research has been dedicated to DL model testing. However, there is still limited w...
Deep Learning (DL) has revolutionized the capabilities of vision-based systems (VBS) in critical app...
The convergence of artificial intelligence, high-performance computing (HPC), and data science bring...
Deep learning (DL) has been widely applied to many domains. Unique challenges in engineering DL syst...
Deep Learning (DL) solutions are increasingly adopted, but how to test them remains a major open res...
Deep learning (DL) models are trained on sampled data, where the distribution of training data diffe...
Deep Learning (DL) components are routinely integrated into software systems that need to perform co...
The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their gen...
An underlying mechanism for successful deep learning (DL) with a limited deep architecture and datas...
It is difficult for humans to distinguish the true and false of rumors, but current deep learning mo...
For the last decade, deep learning (DL) has emerged as a new effective machine learning approach tha...
Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adop...
Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate...
DL frameworks are the basis of constructing all DL programs and models, and thus their bugs could le...
Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A si...
A growing body of research has been dedicated to DL model testing. However, there is still limited w...
Deep Learning (DL) has revolutionized the capabilities of vision-based systems (VBS) in critical app...
The convergence of artificial intelligence, high-performance computing (HPC), and data science bring...
Deep learning (DL) has been widely applied to many domains. Unique challenges in engineering DL syst...
Deep Learning (DL) solutions are increasingly adopted, but how to test them remains a major open res...
Deep learning (DL) models are trained on sampled data, where the distribution of training data diffe...
Deep Learning (DL) components are routinely integrated into software systems that need to perform co...
The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their gen...
An underlying mechanism for successful deep learning (DL) with a limited deep architecture and datas...
It is difficult for humans to distinguish the true and false of rumors, but current deep learning mo...