http://www.bibsonomy.org/burst/tag/machine+languageBibSonomy BuRST Feed for /tag/machine+language2008-07-27T03:46:22+02:00http://www.bibsonomy.org/bibtex/2126d75e944619e66cd60cc9bd97cade7/brazovayeyebrazovayeye2008-06-19T17:46:40+02:00memory, language programming core creature, computation, unicellular complexity, algorithmic algorithms, biological membrane, genetic programming, machine <span style="color:#555555;">Hikeaki <a href="http://www.bibsonomy.org/author/Suzuki">Suzuki</a> </span><em>Artificial Life</em><em>5(4):367--386</em><em>Fall1999. </em>Thu Jun 19 17:46:40 CEST 2008Artificial LifeFall4367--386An Approach to Biological Computation: Unicellular Core-Memory Creatures Evolved Using Genetic Algorithms51999memory, language programming core creature, computation, unicellular complexity, algorithmic algorithms, biological membrane, genetic programming, machine A novel machine language genetic programming system that uses one-dimensional core memories is proposed and simulated. The core is compared to a biochemical reaction space, and in imitation of biological molecules, four types of data words (Membrane, Pure data, Operator, and Instruction) are prepared in the core. A program is represented by a sequence of Instructions. During execution of the core, Instructions are transcribed into corresponding Operators, and Operators modify, create, or transfer Pure data. The core is hierarchically partitioned into sections by the Membrane data, and the data transfer between sections by special channel Operators constitutes a tree data-flow structure among sections in the core. In the experiment, genetic algorithms are used to modify program information. A simple machine learning problem is prepared for the environment data set of the creatures (programs), and the fitness value of a creature is calculated from the Pure data excreted by the creature. Breeding of programs that can output the predefined answer is successfully carried out. Several future plans to extend this system are also discussed.http://www.bibsonomy.org/bibtex/2236646275442c265c2b16ffaf04ad437/brazovayeyebrazovayeye2008-06-19T17:35:00+02:00generation, grammar matched brackets, Evolution, Expressions, Structures, Data Push Functions automatic language Machine Programming, Artificial (ADF), free fitness, Defined Automatic Polish Demes genetic language, Object CFG, Automatically Learning, Stack, down context Dyck induction, Oriented algorithms, code Pareto Reverse programming, <span style="color:#555555;">W. B. <a href="http://www.bibsonomy.org/author/Langdon">Langdon</a> </span><em>Genetic Programming 1996: Proceedings of the First Annual Conference, </em><em>page141--148. </em><em>Stanford University, CA, USA, </em><em>MIT Press, </em><em>28--31 July1996. </em>Thu Jun 19 17:35:00 CEST 2008Stanford University, CA, USAGenetic Programming 1996: Proceedings of the First Annual Conference28--31 July141--148Using Data Structures within Genetic Programming1996generation, grammar matched brackets, Evolution, Expressions, Structures, Data Push Functions automatic language Machine Programming, Artificial (ADF), free fitness, Defined Automatic Polish Demes genetic language, Object CFG, Automatically Learning, Stack, down context Dyck induction, Oriented algorithms, code Pareto Reverse programming, Provision of appropriately structured memory is shown, in some cases, to be advantageous to genetic programming (GP) in comparison with directly addressable indexed memory. Three ``classic'' problems are solved. The first two require the GP to distinguish between sentences that are in a context free language and those that are not given positive and negative training examples of the language. The two languages are, correctly nested brackets and a Dyck language (correctly nested brackets of different types). The third problem is to evaluate integer Reverse Polish (postfix) expressions. Comparisons are made between GP attempting to solve these problems when provided with indexed memory or with stack data structures.http://www.bibsonomy.org/bibtex/2875532499f61f08ebfd594c46d591f8a/brazovayeyebrazovayeye2008-06-19T17:35:00+02:00Reverse induction, Expressions, Structures, Defined Stack, Object language Push Automatically Functions Pareto Automatic Polish genetic down code fitness, Learning, context (ADF), programming, Oriented Machine Demes Evolution, Programming, automatic algorithms, generation, Artificial Data free <span style="color:#555555;">W. B. <a href="http://www.bibsonomy.org/author/Langdon">Langdon</a> </span><em>Research Note, </em><em>RN/96/1. </em><em>UCL, </em><em>Gower Street, London, WC1E 6BT, UK, </em><em>January1996. </em>Thu Jun 19 17:35:00 CEST 2008Gower Street, London, WC1E 6BT, UKJanuaryRN/96/1Using Data Structures within Genetic ProgrammingResearch Note1996Reverse induction, Expressions, Structures, Defined Stack, Object language Push Automatically Functions Pareto Automatic Polish genetic down code fitness, Learning, context (ADF), programming, Oriented Machine Demes Evolution, Programming, automatic algorithms, generation, Artificial Data free In earlier work we showed that GP can automatically generate simple data types (stacks, queues and lists). The results presented herein show, in some cases, provision of appropriately structured memory can indeed be advantageous to GP in comparison with directly addressable indexed memory. Three ``classic'' problems are solved. The first two require the GP to distinguish between sentences that are in a language and those that are not given positive and negative training examples of the language. The two languages are, correctly nested brackets and a Dyck language (correctly nested brackets of different types). The third problem is to evaluate integer Reverse Polish (postfix) expressions. Comparisons are made between GP attempting to solve these problems when provided with indexed memory or with stack data structures.http://www.bibsonomy.org/bibtex/2de199004f39f2510971b56512b97e66c/brazovayeyebrazovayeye2008-06-19T17:35:00+02:00semantic networks, algorithms, information genetic programming, learning, language natural machine processing, retrieval <span style="color:#555555;">Agneta <a href="http://www.bibsonomy.org/author/Bergstrom">Bergstrom</a> and Patricija <a href="http://www.bibsonomy.org/author/Jaksetic">Jaksetic</a> and Peter <a href="http://www.bibsonomy.org/author/Nordin">Nordin</a> </span><em>IUI 2000, </em><em>ACM Press, </em>(<em>2000</em>)Thu Jun 19 17:35:00 CEST 2008IUI 2000Enhancing Information Retrieval by Automatic Acquisition of Textual Relations using Genetic Programming2000semantic networks, algorithms, information genetic programming, learning, language natural machine processing, retrieval We have explored a novel method to find textual relations in electronic documents using genetic programming and semantic networks. This can be used for enhancing information retrieval and simplifying user interfaces. The automatic extraction of relations from text enables easier updating of electronic dictionaries and may reduce interface area both for search input and hit output on small screens such as cell phones and PDAs (Personal Digital Assistants).