Read more
This book explains advanced theoretical andapplication-related issues in grammatical inference, a research area inside theinductive inference paradigm for machine learning. The first three chapters ofthe book deal with issues regarding theoretical learning frameworks; the nextfour chapters focus on the main classes of formal languages according toChomsky's hierarchy, in particular regular and context-free languages; and thefinal chapter addresses the processing of biosequences.
The topics chosen are of foundational interest withrelatively mature and established results, algorithms and conclusions. The bookwill be of value to researchers and graduate students in areas such astheoretical computer science, machine learning, computational linguistics, bioinformatics,and cognitive psychology who are engaged with the study of learning, especiallyof the structure underlying the concept to be learned. Some knowledge ofmathematics and theoretical computer science, including formal language theory,automata theory, formal grammars, and algorithmics, is a prerequisite forreading this book.
List of contents
Introduction.- Gold-Style Learning Theory.- Efficiency in the Identification in the Limit Learning Paradigm.- Learning Grammars and Automata with Queries.- On the Inference of Finite State Automata from Positive and Negative Data.- Learning Probability Distributions Generated by Finite-State Machines.- Distributional Learning of Context-Free and Multiple.- Context-Free Grammars.- Learning Tree Languages.- Learning the Language of Biological Sequences.
Summary
This book explains advanced theoretical and
application-related issues in grammatical inference, a research area inside the
inductive inference paradigm for machine learning. The first three chapters of
the book deal with issues regarding theoretical learning frameworks; the next
four chapters focus on the main classes of formal languages according to
Chomsky's hierarchy, in particular regular and context-free languages; and the
final chapter addresses the processing of biosequences.
The topics chosen are of foundational interest with
relatively mature and established results, algorithms and conclusions. The book
will be of value to researchers and graduate students in areas such as
theoretical computer science, machine learning, computational linguistics, bioinformatics,
and cognitive psychology who are engaged with the study of learning, especially
of the structure underlying the concept to be learned. Some knowledge of
mathematics and theoretical computer science, including formal language theory,
automata theory, formal grammars, and algorithmics, is a prerequisite for
reading this book.
