33,739 Hits in 5.1 sec

Automatically generating features for learning program analysis heuristics [article]

Kwonsoo Chae and Hakjoo Oh and Kihong Heo and Hongseok Yang
2016 arXiv   pre-print
Recently data-driven approaches for building a program analysis have been proposed, which mine existing codebases and automatically learn heuristics for finding a cost-effective abstraction for a given  ...  We present a technique for automatically generating features for data-driven program analyses.  ...  . • We present a framework for automatically generating features for learning analysis heuristics.  ... 
arXiv:1612.09394v1 fatcat:seleeqmrgrbhnfmig35f46mklu

Synthesizing benchmarks for predictive modeling

Chris Cummins, Pavlos Petoumenos, Zheng Wang, Hugh Leather
2017 2017 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)  
We mine open source repositories for program fragments and apply deep learning techniques to automatically construct models for how humans write programs.  ...  We use our generator for OpenCL programs, CLgen, to automatically synthesize thousands of programs and show that learning over these improves the performance of a state of the art predictive model by 1.27  ...  The code and data for this paper are available at:  ... 
doi:10.1109/cgo.2017.7863731 fatcat:4attl72gpfhz5bagpz3ny7rp6i

Automatic Feature Generation for Machine Learning Based Optimizing Compilation

Hugh Leather, Edwin Bonilla, Michael O'Boyle
2009 2009 International Symposium on Code Generation and Optimization  
This paper develops a novel mechanism to automatically find those features which most improve the quality of the machine learned heuristic.  ...  On a benchmark suite of 57 programs, GCC's hard-coded heuristic achieves only 3% of the maximum performance available, while a state of the art machine learning approach with hand-coded features obtains  ...  We have applied this generic technique to automatically learn good features for loop unrolling within GCC.  ... 
doi:10.1109/cgo.2009.21 dblp:conf/cgo/LeatherBO09 fatcat:xlml45gy2nenxmect65metmnqi

Parsing for agile modeling

Oscar Nierstrasz, Jan Kurš
2015 Science of Computer Programming  
This poses a major bottleneck for analyzing software systems programmed in languages for which importers do not already exist.  ...  Unfortunately, building custom parsers for most programming languages is a non-trivial endeavour.  ...  We also thank Niko Schwarz and Erwann Wernli for their helpful comments.  ... 
doi:10.1016/j.scico.2013.11.011 fatcat:6htducknprcp5nsu7dytdnpxpq

Algorithmic Programming Language Identification [article]

David Klein, Kyle Murray, Simon Weber
2011 arXiv   pre-print
Motivated by the amount of code that goes unidentified on the web, we introduce a practical method for algorithmically identifying the programming language of source code.  ...  Our work is based on supervised learning and intelligent statistical features. We also explored, but abandoned, a grammatical approach.  ...  This feature allows us to distinguish between languages like C and Java and languages like Lisp. • FirstWord: We look at the first word of each line of code.  ... 
arXiv:1106.4064v2 fatcat:6rszqb3igrfaxgjucnwtyx3fdi

Heuristic Evaluation Functions for General Game Playing

James E. Clune
2011 Künstliche Intelligenz  
A central challenge in creating effective general game playing programs is that of constructing heuristic evaluation functions from game descriptions.  ...  A game manager program sends the game playing programs a description of a game's rules and objectives in a well-defined game description language.  ...  Acknowledgments We thank Rich Korf for insightful advice throughout the project. Thanks also to Alex Dow, Alex Fukunaga, and Eric Huang for comments on an earlier version of this paper.  ... 
doi:10.1007/s13218-010-0074-7 fatcat:hiadc4py6vdhzmgzdqzqqkf5ou

Milepost GCC: Machine Learning Enabled Self-tuning Compiler

Grigori Fursin, Yuriy Kashnikov, Abdul Wahid Memon, Zbigniew Chamski, Olivier Temam, Mircea Namolaru, Elad Yom-Tov, Bilha Mendelson, Ayal Zaks, Eric Courtois, Francois Bodin, Phil Barnard (+5 others)
2011 International journal of parallel programming  
between program features, run-time behavior and optimizations.  ...  It automatically adapts the internal optimization heuristic at function-level granularity to improve execution time, code size and compilation time of a new program on a given architecture.  ...  These passes can monitor and profile the compilation process or extract data structures needed for generating program features.  ... 
doi:10.1007/s10766-010-0161-2 fatcat:r6s7qcgunzf5hcgllcorvkir4m

Assessing creative problem-solving with automated text grading

Hao-Chuan Wang, Chun-Yen Chang, Tsai-Yen Li
2008 Computers & Education  
language responses automatically.  ...  and enable new technologies for science learning.  ...  Rosé, Yuen-Hsien Tseng, and Chao-Lin Liu for their advices on techniques of language processing and machine learning.  ... 
doi:10.1016/j.compedu.2008.01.006 fatcat:bvo43pmetrgbhfvciwar4pcnjy

Automated Game Design Learning [article]

Joseph C Osborn, Adam Summerville, Michael Mateas
2017 arXiv   pre-print
While general game playing is an active field of research, the learning of game design has tended to be either a secondary goal of such research or it has been solely the domain of humans.  ...  We propose a field of research, Automated Game Design Learning (AGDL), with the direct purpose of learning game designs directly through interaction with games in the mode that most people experience games  ...  Generally speaking, heuristic learning is a way to learn, on a gameby-game basis, about intermediate goals of the game or rough strategies for guiding search.  ... 
arXiv:1707.03333v1 fatcat:ruzmhqo7u5dcxouqexoxj5i7nu

Automated detection and classification of cryptographic algorithms in binary programs through machine learning [article]

Diane Duros Hosfelt
2015 arXiv   pre-print
This thesis will present several methods of leveraging machine learning to automatically discover and classify cryptographic algorithms in compiled binary programs.  ...  Malware and other threats proliferate too quickly for the time-consuming traditional methods of binary analysis to be effective.  ...  If an attacker uses a language such as Python, analysis would become complicated.  ... 
arXiv:1503.01186v1 fatcat:wxznolipurgkzbywvogg3l6pii

An intelligent system for DNA repair

R.R. Joshi
1990 Computers and Mathematics with Applications  
Al~tract--The concepts of stochastic functional and control heuristics for guided learning by discovery are introduced.  ...  Novel features and importance of the associated intelligent program are highlighted along with its applications.  ...  Now with the help of a CH, say, VCH--If C is essential for the rule "f: A nC--,B" then "f: A n(not C)~not B". automatically one new rule would look like (upon searching that no other rule allows the production  ... 
doi:10.1016/0898-1221(90)90042-i fatcat:sa5c6n4zyfdfldhwrko2ebhzda


Ziyu Yao, Daniel S. Weld, Wei-Peng Chen, Huan Sun
2018 Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18  
Under various case studies, we demonstrate that StaQC can greatly help develop data-hungry models for associating natural language with programming language.  ...  Stack Overflow (SO) has been a great source of natural language questions and their code solutions (i.e., question-code pairs), which are critical for many tasks including code retrieval and annotation  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notice herein.  ... 
doi:10.1145/3178876.3186081 dblp:conf/www/YaoWCS18 fatcat:srpfshgrgnhclogc5w2onbpdim

A review of machine learning for automated planning

Sergio Jiménez, Tomás De La Rosa, Susana Fernández, Fernando Fernández, Daniel Borrajo
2012 Knowledge engineering review (Print)  
This paper reviews recent techniques in machine learning for the automatic definition of planning knowledge.  ...  It has been organized according to the target of the learning process: automatic definition of planning action models and automatic definition of planning control knowledge.  ...  Algorithms for n-grams analysis have also been recently applied to learning macro-actions for the heuristic planner FF (Muise et al., 2009 ).  ... 
doi:10.1017/s026988891200001x fatcat:slnkph7hyve3higgkjyd3wydlu

Using meta-heuristics and machine learning for software optimization of parallel computing systems: a systematic literature review

Suejb Memeti, Sabri Pllana, Alécio Binotto, Joanna Kołodziej, Ivona Brandic
2018 Computing  
We review approaches that use machine learning or meta-heuristics for software optimization at compile-time and run-time. Additionally, we discuss challenges and future research directions.  ...  The results of this study may help to better understand the state-of-the-art techniques that use machine learning and meta-heuristics to deal with the complexity of software optimization for parallel computing  ...  Programmers are exposed to various parallel programming languages (often implemented as extensions of general-purpose programming languages such as C and C++), including, OpenMP [72] , MPI [42] , OpenCL  ... 
doi:10.1007/s00607-018-0614-9 fatcat:da2rfxqlcjen5frzfxreimtngm

A Survey of Machine Learning for Big Code and Naturalness

Miltiadis Allamanis, Earl T. Barr, Premkumar Devanbu, Charles Sutton
2018 ACM Computing Surveys  
Research at the intersection of machine learning, programming languages, and software engineering has recently taken important steps in proposing learnable probabilistic models of source code that exploit  ...  We contrast programming languages against natural languages and discuss how these similarities and differences drive the design of probabilistic models.  ...  [38] reduce automatically (without machine learning) a program to a set of data-flow graphs, manually extract features from them.  ... 
doi:10.1145/3212695 fatcat:iuuocyctg5adjmobhc2zw23rfu
« Previous Showing results 1 — 15 out of 33,739 results