Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.
We identify two key properties, independence and continuity, that convert the latent space into a precise and analysis-friendly input space representation for certification.
We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code.
Machine translation software has seen rapid progress in recent years due to the advancement of deep neural networks.
Among the 909 bugs found by OpFuzz, 130 were soundness bugs, the most critical bugs in SMT solvers, and 501 were in the default modes of the solvers.
Software Engineering Programming Languages
To fill this critical gap, we introduce the design and realization of MetaOD, the first metamorphic testing system for object detectors to effectively reveal erroneous detection results by commercial object detectors.
Despite its apparent importance, validating the robustness of machine translation systems is very difficult and has, therefore, been much under-explored.
Learning on the same set of functions (more than 170K in total), \liger significantly outperforms code2seq, the previous state-of-the-art for method name prediction.
In light of a recent study on the mutual influence between robustness and accuracy over 18 different ImageNet models, this paper investigates how training data affect the accuracy and robustness of deep neural networks.
Our evaluation results show that the semantic program embeddings signiﬁcantly outperform the syntactic program embeddings based on token sequences and abstract syntax trees.
Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.
Although there exist many intelligent tutoring systems proposed for geometry proofs, few teach students how to find auxiliary constructions.