Gregory R. Ruth · 1977
To meet the burgeoning software demands of the future the computer will have to take a more active role in the writing of its own software. Many computer tools have been developed that enable the machine to help human software developers. It would be preferable, and in the not too distant future it will be necessary, for the machine to actually take over a substantial part of software development. Automatic programming seeks to do this by moving the human developer up from the implementation level of programming (e.g. COBOL, where the human has to include such details as data and control structures), to a level of programming that is less specific, where it is left to the computer decide the best way to fill in implementation. This article provides a survey of current research and development in automatic programming and a discussion of future directions in this field.
Cited by 8Open access
Guenther Hintze · 1966
Cited by 6
Michael B. Feldman, Michael B. Feldman · 1972
Cited by 0
Elschlager ,Robert, Phillips,Jorge · Defense Technical Information Center (DTIC) · 1979
Automatic Programming (AP) is a new, dynamic, and not precisely defined area of artificial intelligence. This overview discusses the definitions, history, motivating forces and goals of automatic programming and includes a brief description of the basic characteristics and central issues of AP systems. The article begins with a section discussing the various possible definitions of automatic programming, the background in which it has achieved existence, as well as some of its general motivating forces and goals. The next section describes four characteristics of all AP systems: the method by which a user of such a system specifies or describes the desired program, the target language in which the system writes the program, the problem or application area to which the system is addressed, and the approach or operational method employed by the system. Next, a section discusses four basic issues, one or more of which concern all AP systems: the representation and processing of partial or incomplete information; the transformation of structures, and especially the transformation of program descriptions into other descriptions (in this chapter, the term program description includes the user's specification of the desired program, any internal representations of the program, as well as the target language implementation); the efficiency of the target language implementation; and the system's capabilities for aiding in the understanding of the program.
Cited by 1
I Fllllllllfllflfl, Unc Lassifi, I Govt et al. · 2016
Cited by 0
Kevin Igwe, Nelishia Pillay · 2013
Genetic programming (GP) is an evolutionary algorithm which explores a program space rather than a solution space which is typical of other evolutionary algorithms such as genetic algorithms. GP finds solutions to problems by evolving a program, which when implemented will produce a solution. This paper investigates the use of genetic programming for automatic programming. The paper focuses on the procedural/imperative programming paradigm. More specifically the evolution of programs using memory, conditional and iterative programming constructs is investigated. An internal representation language is defined in which to evolve programs. The generational GP algorithm was implemented using the grow method to create the initial population, tournament selection to choose parents and reproduction, crossover and mutation for regeneration purposes. The paper also presents a form of incremental learning which facilitates modularization. The GP approach to automatic programming was tested on ten programming problems that are usually presented to novice programmers in a first year procedural programming course of an undergraduate degree in Computer Science. The GP approach evolved solutions for all ten problems, with incremental learning needed in two instances to produce a solution.
Cited by 11
Mitchell O. Locks · Journal of the American Statistical Association · 1959
Anyone who attempts to process data or perform computations with an automatic digital computer encounters the obstacle of preparing a detailed program in computer code and checking this program out on the computer. Automatic programming techniques help reduce the magnitude and cost of this task. Complex statistical and data processing problems can be programmed with little or no knowledge of the computer code. An example is given of an automatically programmed one way analysis of variance F computation.
Cited by 0
Mitchell O. Locks · Journal of the American Statistical Association · 1959
Cited by 0
William H. Kautz, Edward A. Voorhees, T. A. Jeeves · Communications of the ACM · 1958
No abstract available.
Cited by 5Open access
Riccardo Poli, William B. Langdon · 2012
Cited by 0
Evandro Nunes Regolin, Aurora Pozo · Lecture notes in computer science · 2005
Cited by 26
Philip Gilbert, HOSLER, J., SCHAGER, C. · Defense Technical Information Center (DTIC) · 1962
Abstract : This report is the third of a set of three reports documenting work in the area of automatic compiler generation. The first two reports described the theoretical basis for such a system. This report documents an operating system embodying the concepts described in the first two volumes. The system described in this report allows a programmer to write in FORTRAN, ALGOL, or JOVIAL and produce object code for either the CDC 1604B or the UNIVAC 1218. The system described can be expanded to incorporate other machines or languages. (Author)
Cited by 0
Janet Liebenberg · Lecture notes in networks and systems · 2023
Cited by 2
2008
Most automatic programming research has focused on programs which terminate and which produce output values upon termination. By contrast, programs which operate on streams of data usually do not terminate and usually produce streams of output data during execution. Such stream programs may be specified with a technique which is a generalization of specification techniques for conventional programs The use of transformations also seems to be an appropriate technique for automatically synthesizing stream programs. I.
Cited by 0
Gary Cleveland, Richard L. Piazza, Richard Harvey Brown · 1990
Abstract : This report describes the MITRE developed automatic programming system ISFI and the attempt to use this system in the production and modification of small to moderate sized real-time programs. ISFI is a knowledge- based automatic programming system that has been developed at MITRE during the past 5 years. The ISFI system is based upon the theory that networks of constraints are an appropriate knowledge representation tool for many domains, and illustrates a number of techniques such as propagation and transformation that facilitate inference in constraint networks as a method for code synthesis. Keywords: Artificial intelligence; Knowledge-based systems; Automatic programming; Real time; Software.
Cited by 0
Clayton Lewis · 2022
Automatic programming, as supported by recent language-model based AI systems, potentially allows a new approach to making computation a useful tool for learning, a goal of the Boxer project. This paper shows that the Codex system can be used to support some of the explorations in mathematics for which Boxer has been used. Virtually no knowledge of programming is required. Reflecting on the lessons from this exploration may sharpen the goals we bring to educational computing. What knowledge about computing, as distinct from the ability to creatively use computing, should learners gain?
Cited by 2Open access
Aler, Ricardo · e-Archivo (Carlos III University of Madrid) · 2010
Tutorial de 4 horas de duración, aceptado e impartido en: International Conference in Machine Learning ICML 2006.
Cited by 0Open access
Tim Hussein, Daniel Muenter · 2010
In this paper, we introduce a concept for automated generation of faceted navigation widgets. These widgets are generated on the fly depending on the type of data to be displayed. For this purpose, we use semantic models for data representation and apply generic SPARQL queries, which makes the navigation creation completely independent from the content and structure of the underlying models.
Cited by 0
Charles Rich, Richard C. Waters · Advances in computers · 1993
Cited by 11
Daniel Muenter, Tim Hussein · 2011
Cited by 0