Reflective inductive inference of recursive functions

In this paper, we investigate reflective inductive inference of recursive functions. A reflective IIM is a learning machine that is additionally able to assess its own competence.First, we formalize reflective learning from arbitrary example sequences. Here, we arrive at four different types of reflection: reflection in the limit, optimistic, pessimistic and exact reflection.Then, for learning in the limit, for consistent learning of three different types and for finite learning, we compare the learning power of reflective IIMs with each other as well as with the one of standard IIMs.Finally, we compare reflective learning from arbitrary input sequences with reflective learning from canonical input sequences. In this context, an open question regarding total-consistent identification could be solved: it holds T-CONSa ? T-CONS.

• Publication year

  2002

• Venue

  Theoretical Computer Science

• Publication date

  2002-11-24

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1016/j.tcs.2008.02.022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• On learning of functions refutably

  2003cited by this paper
• Refuting learning revisited

  2001cited by this paper
• Refutable language learning with a neighbor system

  2001cited by this paper
• Learning Recursive Functions Refutably

  2001cited by this paper
• Learning with Refutation

  1998cited by this paper
• Reflecting Inductive Inference Machines and Its Improvement by Therapy

  1996cited by this paper
• Learning and Consistency

  1995cited by this paper
• Towards a Mathematical Theory of Machine Discovery from Facts

  1995cited by this paper
• Reflecting and Self-Confident Inductive Inference Machines

  1995influential reference
• Refutably Probably Approximately Correct Learning

  1994cited by this paper
• Machine Discovery in the Presence of Incomplete or Ambiguous Data

  1994cited by this paper
• One-Sided Error Probabilistic Inductive Inference and Reliable Frequency Identification

  1991cited by this paper
• Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists

  1990cited by this paper
• Inductive Inference of Almost Everywhere Correct Programs by Reliably Working Strategies

  1985cited by this paper
• Combining Postulates of Naturalness in Inductive Inference

  1981cited by this paper
• Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen

  1976cited by this paper
• Some Natural Properties of Strong-Identification in Inductive Inference

  1976cited by this paper
• Limes-Erkennung rekursiver Funktionen durch spezielle Strategien

  1975cited by this paper
• Toward a Mathematical Theory of Inductive Inference

  1975cited by this paper
• Finite automata : behavior and synthesis

  1973cited by this paper
• Theory of Recursive Functions and Effective Computability

  1969cited by this paper
• Language Identification in the Limit

  1967cited by this paper
• A Machine-Independent Theory of the Complexity of Recursive Functions

  1967cited by this paper

• Mining HCI Data for Theory of Mind Induction

  2018influential citation
• Automatic Learning from Repetitive Texts

  2017cites this paper
• Next Generation Learner Modeling by Theory of Mind Model Induction

  2016cites this paper
• Refinement of Adaptivity by Reflection

  2013influential citation
• Confident and consistent partial learning of recursive functions

  2012cites this paper
• On Conservative Learning of R . e . Languages

  2012cites this paper
• Consistent Partial Identification

  2009cites this paper
• On some open problems in reflective inductive inference

  2009influential citation
• Learning recursive functions: A survey

  2008cites this paper
• Learning Recursive Functions by Thomas Zeugmann and Sandra Zilles Division of Computer Science Report Series A November

  2007cites this paper
• Classes with Easily Learnable Subclasses

  2002cites this paper