AutoPandas: neural-backed generators for program synthesis
نویسندگان
چکیده
منابع مشابه
Scoping Constructs for Program Generators
Program generation is the process of generating code in a high-level language (e.g., C, C++, Java) to implement an abstract specification of a program. Generated programs are created by synthesizing and composing code fragments. Binding identifiers in generated code with their correct variable declarations has been the focus of a lot of research work in the context of macro-expansion (e.g., hyg...
متن کاملPCC Framework for Program-Generators
In this paper, we propose a proof-carrying code framework for program-generators. The enabling technique is abstract parsing, a static string analysis technique, which is used as a component for generating and validating certificates. Our framework provides an efficient solution for certifying program-generators whose safety properties are expressed in terms of the grammar representing the gene...
متن کاملNeural networks for FDTD-backed permittivity reconstruction
Purpose – To outline different versions of a novel method for accurate and efficient determining the dielectric properties of arbitrarily shaped materials. Design/methodology/approach – Complex permittivity is found using an artificial neural network procedure designed to control a 3D FDTD computation of S-parameters and to process their measurements. Network architectures are based on multilay...
متن کاملRecent Advances in Neural Program Synthesis
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence. The successes in these problems has led researchers to consider the possibilities for intelligent systems to tackle a problem that humans have only recently themselves considered: program synthesis. This challenge is unlike others such as object recogn...
متن کاملNeural Program Synthesis with Priority Queue Training
We consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. We employ an iterative optimization scheme, where we train an RNN on a dataset of K best programs from a priority queue of the generated programs so far. Then, we synthesize new programs and add them to the priority queue by samplin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ACM on Programming Languages
سال: 2019
ISSN: 2475-1421
DOI: 10.1145/3360594