Many programs have important functional-correctness properties that involve sophisticated mathematical relationships between numerical variables. Additionally, many programs have important numerical properties that ...

Software continues to be vital to the modern world, and as its ubiquity increases, its correctness becomes ever more valuable. Unfortunately, fundamental mathematical constraints on static analysis preclude the possibility ...

A crucial component of modern machine learning systems is learning input representations which can be used for prediction tasks. The expensive cost of labelling and easy availability of unlabelled data has led to the ...

Regulatory network reconstruction is an ongoing field of research that biologists have been pressing with considerable effort. Although several computational methods have been investigated, inferred networks still severely ...

Data augmentation (DA) is a common technique in training machine learning models. For example in image classifications, people augment image datasets by random cropping, rotating, and adding random noises. Another trending ...

There is an intrinsic tension between the incentives for developers of commodity software and the desires of users of commodity software. Developers of commodity software must support a multitude of users and use cases, ...