Maintaining regularity and generalization in data using the minimum description length principle and genetic algorithm: Case of grammatical inference

详细信息    查看全文

• 作者：Hari Mohan Pandey^a ; ^{profharimohanpandey@gmail.com}Author Vitae ; Ankit Chaudhary^bAuthor Vitae ; Deepti Mehrotra^cAuthor Vitae ; Graham Kendall^dAuthor Vitae
• 关键词：ANS ; Accepting negative sample ; APS ; Accepting positive sample ; BMODA ; Bit masking oriented data structure ; BNF ; Backus Naur Form ; BBP ; Boolean based procedure ; CFL ; Context free language ; CFG ; Context free grammar ; CS ; Chromosome size ; CM ; Crossmask/crossover mask ; CR ; Crossover rate ; DFA ; Deterministic finite automata ; DL ; Description Length ; DSL ; Domain-Specific Language ; EA ; Evolutionary algorithm ; EMP ; Elite Mating Pool Genetic Algorithm ; GI ; Grammatical inference ; GA ; Genetic algorithm wit
• 刊名：Swarm and Evolutionary Computation
• 出版年：2016
• 出版时间：December 2016
• 年：2016
• 卷：31
• 期：Complete
• 页码：11-23
• 全文大小：1554 K
• 卷排序：31

文摘

Discussion on the challenges in inference system. A background theory of grammar induction is presented. Brief description of minimum description length principle and its connection to inference system. Detailed discussion of the proposed genetic algorithm for grammatical inference. Comparative analysis, discussion, observation and statistical test are given in an effective manner.