The Consistency Dimension and Distribution-Dependent Learning from Queries (Extended Abstract)
نویسندگان
چکیده
We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on the instance space, both as an application of the tools developed from the combinatorial characterization and as models of independent interest.
منابع مشابه
The Consistency Dimension and Distribution-dependent Learning from Queries (extended Abstract with Appendices)
We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnabil-ity via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on...
متن کاملCombinatorial Dimension for Exact Learning via Queries Jos
We introduce an abstract model of exact learning via queries that can be instantiated to all the query learning models currently in use, while being closer to them than previous unifying attempts. We present a characterization of those Boolean function classes learnable in this abstract model, in terms of a new combinatorial notion that we introduce, the abstract identi cation dimension. Then w...
متن کاملA New Abstract Combinatorial Dimension for Exact Learning via Queries
We introduce an abstract model of exact learning via queries that can be instantiated to all the query learning models currently in use, while being closer to them than previous uniicatory attempts. We present a characterization of those Boolean function classes learnable in this abstract model, in terms of a new combinatorial notion that we introduce, the abstract identiication dimension. Then...
متن کاملThe consistency dimension and distribution-dependent learning from queries
We prove a new combinatorial characterization of polynomial learnability from equiva lence queries and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space Then we propose and study two models of query learning in which there is a probability distribution on t...
متن کاملExpansion of Location Theories of Firms and Products’ Consistency Using Triangular Distribution Approach
Abstract O ne of the main criticisms of location models is simplistic assumptions concerning the consumers’ distribution on the street or city. The location models usually make use of uniform distribution of consumers while it is not true in reality, and mostly the consumers’ accumulation is more in the city centers rather than suburb areas. This study deals with selectio...
متن کامل