Algorithmic Learning Theory

Towards efficient inductive synthesis from input/output examples.- Deductive plan generation.- From specifications to programs: Induction in the service of synthesis.- Average case analysis of pattern language learning algorithms.- Enumerable classes of total recursive functions: Complexity of inductive inference.- Derived sets and inductive inference.- Therapy plan generation as program synthesis.- A calculus for logical clustering.- Learning with higher order additional information.- Efficient learning of regular expressions from good examples.- Identifying nearly minimal Gödel numbers from additional information.- Co-learnability and FIN-identifiability of enumerable classes of total recursive functions.- On case-based represent ability and learnability of languages.- Rule-generating abduction for recursive prolog.- Fuzzy analogy based reasoning and classification of fuzzy analogies.- Explanation-based reuse of prolog programs.- Constructive induction for recursive programs.- Training digraphs.- Towards realistic theories of learning.- A unified approach to inductive logic and case-based reasoning.- Three decades of team learning.- On-line learning with malicious noise and the closure algorithm.- Learnability with restricted focus of attention guarantees noise-tolerance.- Efficient algorithm for learning simple regular expressions from noisy examples.- A note on learning DNF formulas using equivalence and incomplete membership queries.- Identifying regular languages over partially-commutative monoids.- Classification using information.- Learning from examples with typed equational programming.- Finding tree patterns consistent with positive and negative examples using queries.- Program synthesis in the presence of infinite number of inaccuracies.- On monotonic strategies for learning r.e. languages.- Language learning under various types of constraint combinations.- Synthesis algorithm for recursive processes by ?-calculus.- Monotonicity versus efficiency for learning languages from texts.- Learning concatenations of locally testable languages from positive data.- Language learning from good examples.- Machine discovery in the presence of incomplete or ambiguous data.- Set-driven and rearrangement-independent learning of recursive languages.- Refutably probably approximately correct learning.- Inductive inference of an approximate concept from positive data.- Efficient distribution-free population learning of simple concepts.- Constructing predicate mappings for Goal-Dependent Abstraction.- Learning languages by collecting cases and tuning parameters.- Mutual information gaining algorithm and its relation to PAC-learning algorithm.- Inductive inference of monogenic pure context-free languages.