Flexible Example-Based Program Synthesis on Tree-Structured Function Compositions

We introduce a flexible program synthesis system whose task is to predict function compositions that transform given inputs to their corresponding given outputs. We process input lists in a sequential manner, allowing the system to generalize to a wide range of input lengths. We separate the operato...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:SN computer science Ročník 3; číslo 3; s. 218
Hlavní autoři: Mucsányi, Bálint, Gyarmathy, Bálint, Czapp, Ádám, Pintér, Balázs
Médium: Journal Article
Jazyk:angličtina
Vydáno: Singapore Springer Nature Singapore 01.05.2022
Springer Nature B.V
Témata:
Algorithms
Composition
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Information Systems and Communication Service
Neural networks
Operators (mathematics)
Original Research
Parameters
Pattern Recognition and Graphics
Pattern Recognition Applications and Methods
Software Engineering/Programming and Operating Systems
Synthesis
Vision
Gated recurrent unit
Tree-structured composition
Recurrent neural network
Programming by examples
Program synthesis
Beam search
ISSN:2662-995X, 2661-8907
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We introduce a flexible program synthesis system whose task is to predict function compositions that transform given inputs to their corresponding given outputs. We process input lists in a sequential manner, allowing the system to generalize to a wide range of input lengths. We separate the operator and the operand in the lambda functions of the used higher order functions to achieve significantly wider numeric parameter ranges compared to the previous works. The evaluations show that this approach is competitive with state-of-the-art systems, while it is much more flexible in terms of the input length, the parameters of the lambda functions, and the integer range of the inputs and outputs. We extend the system to handle tree-structured function compositions by introducing two additional functions (zip_with, copy) and the ability to represent unfinished function compositions during the synthesis process. The extended system achieves state-of-the-art results while synthesizing complex function compositions with multiple forks. We believe that flexibility in these aspects is an important step towards solving real-world problems with example-based program synthesis.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2662-995X
2661-8907
DOI:10.1007/s42979-022-01090-4